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

    Neuronpedia

    INDEX
    Explanations

    numerical comparisons and ranges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igos
    -0.15
    دÙĨ
    -0.15
     Regents
    -0.14
    .mas
    -0.14
    ssp
    -0.14
    ãģıãģł
    -0.14
    antor
    -0.13
    PY
    -0.13
     fund
    -0.13
     Olson
    -0.13
    POSITIVE LOGITS
    andom
    0.16
    нина
    0.15
     Toxic
    0.14
    bearing
    0.14
    _Helper
    0.14
    ADER
    0.14
    ìĽĢ
    0.14
    filled
    0.14
    ettle
    0.14
    uyla
    0.14
    Act Density 0.114%

    No Known Activations