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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the term "zero" and its variations within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    md
    -0.17
    igu
    -0.17
    ÙĨدا
    -0.16
    ibur
    -0.15
    ris
    -0.15
    ament
    -0.14
    yny
    -0.14
     Capt
    -0.14
    -muted
    -0.14
    allis
    -0.14
    POSITIVE LOGITS
     tolerance
    0.28
    /null
    0.25
    -sum
    0.21
    MQ
    0.20
    /full
    0.20
     tolerant
    0.19
    olerance
    0.19
    -zero
    0.19
    th
    0.18
     sum
    0.18
    Act Density 0.019%

    No Known Activations