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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to members of Congress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phal
    -0.85
    istically
    -0.75
    olean
    -0.66
     Siberian
    -0.65
     Finnish
    -0.64
    theless
    -0.64
    zsche
    -0.63
     Brist
    -0.62
    ahime
    -0.62
     Firefly
    -0.62
    POSITIVE LOGITS
    rint
    1.22
    orters
    1.19
    utation
    1.13
    ository
    1.08
    orter
    1.07
    utations
    1.01
    orted
    0.99
    rieve
    0.99
    ublic
    0.98
    ositories
    0.95
    Act Density 0.009%

    No Known Activations