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

    Neuronpedia

    INDEX
    Explanations

    pronouns and identity-related words

    oai_token-act-pair · gpt-3.5-turbo

    references to personal identity and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assembly
    -0.58
     Round
    -0.57
     Shelby
    -0.56
    entary
    -0.55
    atory
    -0.54
     Associated
    -0.53
    atel
    -0.52
     Gene
    -0.52
     Nationwide
    -0.52
     Millennium
    -0.51
    POSITIVE LOGITS
    'll
    1.06
    've
    1.04
    'd
    0.98
    're
    0.89
     owe
    0.84
     reluct
    0.81
     encount
    0.80
     knew
    0.78
    ATHER
    0.75
     swore
    0.71
    Act Density 0.599%

    No Known Activations