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

    Neuronpedia

    INDEX
    Explanations

    expressions of willingness or readiness to engage or take action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OrDefault
    -0.17
    uga
    -0.17
    egl
    -0.16
    yun
    -0.15
    zan
    -0.15
    olley
    -0.15
    affle
    -0.14
    ä¼ģ
    -0.14
    as
    -0.14
    aso
    -0.14
    POSITIVE LOGITS
    ness
    0.29
     willing
    0.20
    NESS
    0.20
    iam
    0.18
    ToUpdate
    0.17
     suspension
    0.17
    /un
    0.17
    kommen
    0.17
    ough
    0.17
    antes
    0.16
    Act Density 0.016%

    No Known Activations