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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical concepts of parity and classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FML
    -0.16
    aurus
    -0.15
    ần
    -0.14
    emploi
    -0.14
    dj
    -0.14
    orian
    -0.14
    ovan
    -0.14
    scape
    -0.14
    erdale
    -0.14
     Valle
    -0.14
    POSITIVE LOGITS
     tr
    0.16
    aspect
    0.16
     Schn
    0.16
    abr
    0.15
     Adler
    0.14
    _absolute
    0.14
    AMENT
    0.14
    Aspect
    0.14
     Aspect
    0.14
     preg
    0.13
    Act Density 0.016%

    No Known Activations