Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    contractions such as 'let's' and possessive forms like 'Queen's'

    oai_token-act-pair · gpt-3.5-turbo

    phrases that begin with "Let's" or related to suggestions or proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.68
    ELD
    -0.66
    eur
    -0.61
    76561
    -0.61
    Downloadha
    -0.59
     discrep
    -0.58
    luster
    -0.58
    avorable
    -0.57
    existent
    -0.57
    produced
    -0.56
    POSITIVE LOGITS
     pretend
    1.10
     assume
    1.09
     suppose
    1.03
     recap
    0.98
     simplify
    0.97
     say
    0.96
     face
    0.96
     start
    0.95
     talk
    0.95
     summarize
    0.95
    Act Density 0.033%

    No Known Activations