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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to heat and thermal processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ration
    -0.49
     Lap
    -0.48
    dire
    -0.47
     negative
    -0.46
     least
    -0.46
    ostante
    -0.46
     Alles
    -0.46
    negative
    -0.45
     חיצוניים
    -0.45
     jau
    -0.45
    POSITIVE LOGITS
     heaters
    0.93
     heater
    0.91
    heat
    0.88
     heat
    0.86
    Heat
    0.80
     Heater
    0.79
     ControllerBase
    0.79
    horses
    0.79
    +#+#
    0.78
     horses
    0.75
    Act Density 0.149%

    No Known Activations