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

    Neuronpedia

    INDEX
    Explanations

    numerical values and quantities related to capacity or measurement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uan
    -0.16
    iro
    -0.15
    izo
    -0.15
    ccion
    -0.14
    zo
    -0.14
    wed
    -0.14
    _CONSTANT
    -0.14
     Amph
    -0.14
    rub
    -0.14
     Bands
    -0.14
    POSITIVE LOGITS
    ISTA
    0.15
     Shields
    0.14
     hyp
    0.14
    esty
    0.14
    996
    0.14
     Fab
    0.13
    oses
    0.13
     Nome
    0.13
    709
    0.13
    usted
    0.13
    Act Density 0.084%

    No Known Activations