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

    Neuronpedia

    INDEX
    Explanations

    first person pronouns and associated verbs expressing personal actions

    oai_token-act-pair · gpt-3.5-turbo

    first-person and second-person pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quartered
    -0.74
    rehend
    -0.74
    imum
    -0.71
    aign
    -0.71
    20439
    -0.68
    cephal
    -0.66
    angan
    -0.62
    handled
    -0.62
     Virtue
    -0.61
    ignt
    -0.61
    POSITIVE LOGITS
    'll
    0.79
    iral
    0.74
     forgot
    0.73
     kidding
    0.73
    're
    0.73
    've
    0.72
     ain
    0.71
     vom
    0.69
     Didn
    0.68
     Naw
    0.68
    Act Density 0.306%

    No Known Activations