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

    Neuronpedia

    INDEX
    Explanations

    references to coal and its related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    coal plants, mines, burning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     senses
    -0.46
     Serrano
    -0.46
     SSS
    -0.45
     Wylie
    -0.45
     محفوظة
    -0.43
     XXXVII
    -0.42
    Formik
    -0.42
     Phillips
    -0.41
     Farrar
    -0.41
    RegistryLite
    -0.41
    POSITIVE LOGITS
     coal
    2.13
     Coal
    2.06
    Coal
    2.00
    coal
    1.88
     COAL
    1.76
    COAL
    1.58
     coals
    1.22
     carbón
    1.16
    煤
    1.15
     charbon
    1.02
    Act Density 0.002%

    No Known Activations