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

    Neuronpedia

    INDEX
    Explanations

    references to thermal or heat-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orithmic
    -0.91
     برانيه
    -0.84
    وصلات
    -0.81
    rungsseite
    -0.80
    Rohy
    -0.78
    BufferException
    -0.78
     Rufus
    -0.77
     Alina
    -0.77
     citoy
    -0.77
     Davy
    -0.76
    POSITIVE LOGITS
     HEAT
    1.38
     Heat
    1.28
    heat
    1.26
     heat
    1.25
    HEAT
    1.25
    Heat
    1.12
     heats
    1.03
    heatmap
    0.96
     Heath
    0.93
     Heiz
    0.90
    Act Density 0.089%

    No Known Activations