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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols or operators associated with addition

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    complexContent
    -0.83
    LookAnd
    -0.79
     vPvB
    -0.77
    septic
    -0.77
    jsii
    -0.74
    pushFollow
    -0.73
    nasium
    -0.73
    DebuggerNonUser
    -0.71
     Baillargeon
    -0.71
    setVerticalGroup
    -0.69
    POSITIVE LOGITS
     humains
    0.65
     terminée
    0.61
     pouvaient
    0.60
     fédé
    0.59
     NotImplemented
    0.58
     intitulée
    0.57
     insectes
    0.56
     humaines
    0.56
     démocr
    0.55
     portata
    0.55
    Act Density 0.003%

    No Known Activations