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

    Neuronpedia

    INDEX
    Explanations

    references to smoke and fires

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icit
    -0.14
    uner
    -0.14
    quette
    -0.14
    زÙħ
    -0.13
     Slider
    -0.12
    į¼
    -0.12
     Crash
    -0.12
     audi
    -0.12
     scissors
    -0.12
     Firm
    -0.12
    POSITIVE LOGITS
     bill
    0.39
     clouds
    0.32
     smoke
    0.31
     wa
    0.31
     haze
    0.31
     cloud
    0.30
     emitted
    0.29
     emissions
    0.29
     inhal
    0.29
     drifting
    0.28
    Act Density 0.070%

    No Known Activations