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

    Neuronpedia

    INDEX
    Explanations

    comparisons between different entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases involving the word "versus."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olog
    -0.83
    unes
    -0.81
    shire
    -0.79
    obal
    -0.77
    seed
    -0.76
    lied
    -0.75
    ocrine
    -0.74
    omical
    -0.74
    ERN
    -0.72
     Dise
    -0.71
    POSITIVE LOGITS
    hill
    0.73
    pecting
    0.66
     nil
    0.65
     mindset
    0.63
     LCD
    0.62
     await
    0.60
     expecting
    0.60
     bureaucratic
    0.59
     trusting
    0.59
     ugly
    0.58
    Act Density 0.015%

    No Known Activations