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

    Neuronpedia

    INDEX
    Explanations

    references to supporting actors or elements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.85
    ьаж
    -0.84
    Ethnicity
    -0.79
    脚注の使い方
    -0.74
    HideFlags
    -0.70
    apunov
    -0.70
    Референце
    -0.68
     الحره
    -0.68
     faute
    -0.67
    RTEX
    -0.66
    POSITIVE LOGITS
     supporting
    1.57
    Supporting
    1.44
     Supporting
    1.44
    supporting
    1.39
    Helping
    1.26
     helping
    1.21
     Helping
    1.20
    helping
    1.06
     guiding
    1.02
     enabling
    0.92
    Act Density 0.147%

    No Known Activations