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

    Neuronpedia

    INDEX
    Explanations

    instances of specific keywords and phrases related to current events and politics

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iously
    -0.68
    ").
    -0.67
    rists
    -0.58
    »
    -0.57
    esi
    -0.57
    endo
    -0.55
    mask
    -0.54
    uci
    -0.54
    "></
    -0.53
    Laughs
    -0.53
    POSITIVE LOGITS
     meanwhile
    1.22
     however
    1.09
     coupled
    0.90
     namely
    0.90
     moreover
    0.85
    channelAvailability
    0.84
     huh
    0.83
     including
    0.82
     along
    0.79
    20439
    0.77
    Act Density 0.373%

    No Known Activations