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

    Neuronpedia

    INDEX
    Explanations

    phrases involving the concept of willingness or readiness to engage in activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egl
    -0.21
    OrDefault
    -0.17
    clamation
    -0.16
    edy
    -0.15
    aso
    -0.15
    erp
    -0.15
    PERT
    -0.15
    pic
    -0.14
    oshi
    -0.14
    rese
    -0.14
    POSITIVE LOGITS
    ness
    0.23
     suspension
    0.20
     willing
    0.19
    kommen
    0.18
    /un
    0.17
     Suspension
    0.17
    boro
    0.16
    NESS
    0.15
    power
    0.15
    antes
    0.15
    Act Density 0.017%

    No Known Activations