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

    Neuronpedia

    INDEX
    Explanations

    words related to granting, giving, and allocation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    serter
    -0.15
     pledge
    -0.15
    uet
    -0.15
    apis
    -0.14
    ars
    -0.14
     ÑĩÑĥж
    -0.14
    _elems
    -0.14
    acock
    -0.14
    ape
    -0.14
    chemes
    -0.14
    POSITIVE LOGITS
     емÑĥ
    0.23
     him
    0.22
     ihm
    0.20
     йомÑĥ
    0.19
     ей
    0.18
     us
    0.17
    him
    0.17
     directions
    0.16
     индивидÑĥ
    0.16
     them
    0.16
    Act Density 0.112%

    No Known Activations