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

    Neuronpedia

    INDEX
    Explanations

    references to zero tolerance policies and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igu
    -0.14
    md
    -0.14
    spec
    -0.14
    yyy
    -0.14
     Minh
    -0.14
    gal
    -0.14
    cret
    -0.14
    yny
    -0.14
    agu
    -0.14
     Colleg
    -0.14
    POSITIVE LOGITS
     tolerance
    0.29
    /null
    0.26
    ing
    0.24
     tolerant
    0.22
    -sum
    0.22
     gravity
    0.21
    ed
    0.21
    ToOne
    0.21
     sum
    0.19
    th
    0.19
    Act Density 0.016%

    No Known Activations