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

    Neuronpedia

    INDEX
    Explanations

    pronouns and verbs related to actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "it" and other relevant personal pronouns in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jri
    -0.78
    aukee
    -0.76
    ussen
    -0.71
     Atkinson
    -0.69
    amaz
    -0.65
    ibaba
    -0.64
    itcher
    -0.63
    icist
    -0.63
    icter
    -0.62
    itive
    -0.62
    POSITIVE LOGITS
    'd
    0.95
    'll
    0.93
    've
    0.87
     could
    0.87
     should
    0.86
    're
    0.86
     ought
    0.85
     shouldn
    0.85
    OULD
    0.81
     might
    0.79
    Act Density 0.244%

    No Known Activations