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

    Neuronpedia

    INDEX
    Explanations

    expressions of warmth and comfort

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     referenties
    -0.82
     maș
    -0.76
    parsedMessage
    -0.73
     împre
    -0.72
     acorns
    -0.69
     néglig
    -0.69
     CGPA
    -0.69
     piele
    -0.68
    InjectAttribute
    -0.68
    yntaxException
    -0.67
    POSITIVE LOGITS
     warm
    3.56
     Warm
    3.34
    Warm
    3.27
    warm
    3.25
     WARM
    3.01
    WARM
    2.77
     warmer
    2.68
     warmth
    2.67
     warms
    2.58
     warmest
    2.45
    Act Density 0.047%

    No Known Activations