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

    Neuronpedia

    INDEX
    Explanations

    personal experiences and actions related to life events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the pronoun "I"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Azerbai
    -0.65
    tains
    -0.63
     Shak
    -0.59
     Vald
    -0.58
     Highest
    -0.58
     Hazard
    -0.57
     Uriel
    -0.56
    ryption
    -0.56
    pires
    -0.56
     Jarrett
    -0.56
    POSITIVE LOGITS
    've
    1.29
    'm
    1.29
    'd
    1.12
     suppose
    1.09
    'll
    1.06
     guess
    0.95
    ggy
    0.93
    rises
    0.90
     knew
    0.90
     presume
    0.87
    Act Density 0.332%

    No Known Activations