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

    Neuronpedia

    INDEX
    Explanations

    numerical data and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     '
    -0.16
     "
    -0.15
     bil
    -0.15
     trick
    -0.15
    Envelope
    -0.15
     demi
    -0.14
    iesen
    -0.14
     arte
    -0.14
     pretty
    -0.14
    ertools
    -0.14
    POSITIVE LOGITS
    ırak
    0.15
     negligible
    0.15
    JKLM
    0.15
     nonzero
    0.14
    .Ass
    0.14
     Homework
    0.14
    >tag
    0.13
    dech
    0.13
    ))?
    0.13
     Modeling
    0.13
    Act Density 0.093%

    No Known Activations