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

    Neuronpedia

    INDEX
    Explanations

    phrases that imply perception, consideration, or interpretation of an entity or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AutoScaleMode
    -0.60
     nahilalakip
    -0.59
     oprot
    -0.56
    ModelAdmin
    -0.47
    tagHelperRunner
    -0.47
    Diweddarwch
    -0.47
    Kanpo
    -0.46
    ViewFeatures
    -0.46
    ScopeManager
    -0.45
    HasAnnotation
    -0.45
    POSITIVE LOGITS
     a
    0.57
     becoming
    0.56
    视为
    0.51
     Sebagai
    0.49
     an
    0.47
    当成
    0.46
    作为
    0.46
     considered
    0.45
    becoming
    0.44
     sebagai
    0.44
    Act Density 0.550%

    No Known Activations