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

    Neuronpedia

    INDEX
    Explanations

    descriptions related to fire and warmth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eof
    -0.17
    ubat
    -0.14
     Bloody
    -0.14
    opak
    -0.14
    acco
    -0.13
    ÌĨ
    -0.13
    796
    -0.13
     Refriger
    -0.13
    /Dk
    -0.13
    VEC
    -0.13
    POSITIVE LOGITS
     burn
    0.65
     burning
    0.64
     burns
    0.60
    burn
    0.58
     Burn
    0.57
     burned
    0.56
    Burn
    0.54
     Burning
    0.53
     burnt
    0.53
     flames
    0.52
    Act Density 0.334%

    No Known Activations