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

    Neuronpedia

    INDEX
    Explanations

    sentences with pronouns referring to specific individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    references to groups of people and individuals involved in actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Eleven
    -0.69
    GMT
    -0.65
    gate
    -0.62
    wake
    -0.62
    geries
    -0.61
    wick
    -0.60
    itu
    -0.59
    violent
    -0.58
    population
    -0.58
     Um
    -0.57
    POSITIVE LOGITS
     drew
    0.86
     wrote
    0.86
     hoped
    0.83
     also
    0.83
    'll
    0.82
     did
    0.80
     ensured
    0.79
    've
    0.79
     gave
    0.78
     recommends
    0.78
    Act Density 0.449%

    No Known Activations