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

    Neuronpedia

    INDEX
    Explanations

    references to heat and thermal phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orithmic
    -0.90
     myeloma
    -0.79
    AccessorTable
    -0.77
    rungsseite
    -0.73
     Stretcher
    -0.69
    naires
    -0.68
    naire
    -0.68
    ganu
    -0.68
     Janssen
    -0.67
     Franch
    -0.67
    POSITIVE LOGITS
     heat
    2.19
     Heat
    2.07
    heat
    2.02
     HEAT
    1.99
    Heat
    1.94
    HEAT
    1.88
     heats
    1.61
    heatmap
    1.30
     Wärme
    1.23
     chaleur
    1.15
    Act Density 0.063%

    No Known Activations