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

    Neuronpedia

    INDEX
    Explanations

    terms related to zero quantities or zero tolerance policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wend
    -0.16
    yny
    -0.15
    igu
    -0.15
    md
    -0.15
    ych
    -0.15
    vor
    -0.14
     Capt
    -0.14
    ict
    -0.14
    allis
    -0.14
    wil
    -0.14
    POSITIVE LOGITS
     tolerance
    0.29
    /null
    0.22
    -sum
    0.21
     tolerant
    0.20
    MQ
    0.20
    olerance
    0.19
    ing
    0.19
    -zero
    0.19
    tol
    0.18
    ToOne
    0.18
    Act Density 0.020%

    No Known Activations