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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical terms or notation related to physical models or equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.20
    ly
    -0.16
    estroy
    -0.15
    able
    -0.15
    o
    -0.14
    et
    -0.14
    of
    -0.14
    -
    -0.14
    e
    -0.14
    ward
    -0.14
    POSITIVE LOGITS
    ÏĮÏģ
    0.16
     anale
    0.16
    ÅĻÃŃt
    0.16
    efon
    0.15
    /goto
    0.15
    ÏĥÏĥα
    0.15
    chein
    0.14
    _mD
    0.14
    OutOfRangeException
    0.14
    _tF
    0.14
    Act Density 0.063%

    No Known Activations