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

    Neuronpedia

    INDEX
    Explanations

    instances of the pronoun "he" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aren
    -0.16
    ظÙĩ
    -0.16
     Were
    -0.15
    *=*=
    -0.15
    _compiler
    -0.14
     são
    -0.14
     weren
    -0.14
    luv
    -0.14
    ajs
    -0.14
    Were
    -0.14
    POSITIVE LOGITS
    /her
    0.44
    /she
    0.44
     himself
    0.42
    aviest
    0.30
    avier
    0.29
    inous
    0.28
    arken
    0.27
    idelberg
    0.26
    aped
    0.26
     Himself
    0.25
    Act Density 0.351%

    No Known Activations