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

    Neuronpedia

    INDEX
    Explanations

    words associated with warmth and positive emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.91
     кӀ
    -0.69
    évaluateur
    -0.66
     تانيه
    -0.66
    libft
    -0.65
    ]--;
    -0.64
    ècie
    -0.62
    InjectAttribute
    -0.61
    modelBuilder
    -0.61
    thâu
    -0.60
    POSITIVE LOGITS
    warm
    0.95
    WARM
    0.95
     warm
    0.92
     weather
    0.88
    Warm
    0.88
     Warm
    0.87
     WARM
    0.82
     warms
    0.81
     temperatures
    0.73
     warming
    0.70
    Act Density 0.038%

    No Known Activations