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

    Neuronpedia

    INDEX
    Explanations

    specific programming or technical terms related to statistical distributions in code or mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    them
    -0.86
     THEM
    -0.77
     eux
    -0.64
     lui
    -0.62
    Them
    -0.60
     Them
    -0.59
    eux
    -0.55
     mnie
    -0.55
    him
    -0.53
     henne
    -0.53
    POSITIVE LOGITS
     there
    1.71
     we
    1.56
     it
    1.46
     they
    1.46
    there
    1.17
     you
    1.14
     the
    1.06
     فإن
    0.99
     many
    0.98
     he
    0.97
    Act Density 0.637%

    No Known Activations