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

    Neuronpedia

    INDEX
    Explanations

    pronouns and possessive pronouns referring to people

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Amen
    -0.81
     ..."
    -0.68
    catentry
    -0.66
    isher
    -0.64
    Untitled
    -0.63
    venge
    -0.62
    )"
    -0.60
    }}
    -0.59
    )",
    -0.59
    limits
    -0.58
    POSITIVE LOGITS
    've
    1.00
    'd
    0.94
    'll
    0.83
    're
    0.80
    pherd
    0.78
     didn
    0.78
     certainly
    0.78
    miah
    0.76
     grew
    0.75
    pard
    0.73
    Act Density 0.305%

    No Known Activations