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

    Neuronpedia

    INDEX
    Explanations

    expressions of warmth and friendliness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     getItemCount
    -0.87
    parsedMessage
    -0.86
    RegistryLite
    -0.85
    rungsseite
    -0.85
    ="@+
    -0.78
    例句
    -0.77
    mtd
    -0.75
     referenties
    -0.74
     Ferdinando
    -0.74
     épar
    -0.73
    POSITIVE LOGITS
    warm
    1.55
     Warm
    1.54
    WARM
    1.50
     warm
    1.49
     WARM
    1.46
    Warm
    1.43
     warmth
    1.39
     warms
    1.35
     warmer
    1.21
     warmed
    1.15
    Act Density 0.047%

    No Known Activations