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

    Neuronpedia

    INDEX
    Explanations

    expressions emphasizing significant attributes or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FloatField
    -0.60
    en
    -0.56
    كت
    -0.56
    emo
    -0.56
    lin
    -0.55
    DeleteMapping
    -0.55
    IDO
    -0.54
     Cleo
    -0.53
     marmo
    -0.52
    IntegerField
    -0.52
    POSITIVE LOGITS
    ----</
    0.93
     Roskov
    0.89
    :✨
    0.89
     SUCH
    0.88
    outchouc
    0.87
    PostExecute
    0.86
    olesale
    0.84
    ridescent
    0.84
    Such
    0.84
     ProtoMessage
    0.83
    Act Density 0.088%

    No Known Activations