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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating decisiveness or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ibarra
    -0.66
     Slee
    -0.64
    ành
    -0.61
     coper
    -0.59
     SSS
    -0.59
    beep
    -0.59
     Haga
    -0.58
     Griswold
    -0.57
    ings
    -0.57
     ALO
    -0.54
    POSITIVE LOGITS
    VIAF
    0.97
     defaultstate
    0.89
     كومونز
    0.88
     ProtoMessage
    0.87
    ly
    0.86
    RenderAtEndOf
    0.85
     للمعارف
    0.85
    ς
    0.81
    存于互联网档案馆
    0.79
    posedge
    0.75
    Act Density 0.500%

    No Known Activations