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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "willing" and variations of its usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shal
    -0.17
    RunLoop
    -0.17
    egl
    -0.16
    efe
    -0.15
    itler
    -0.15
    aso
    -0.15
    .isNullOrEmpty
    -0.15
    ÎŃν
    -0.15
    ROUT
    -0.15
    اÙĦÙĩ
    -0.15
    POSITIVE LOGITS
    -bodied
    0.20
    ness
    0.19
     to
    0.18
    ToShow
    0.17
    imestep
    0.17
    ToUpdate
    0.17
     sacrifice
    0.17
    kommen
    0.16
    /ag
    0.16
    isco
    0.16
    Act Density 0.015%

    No Known Activations