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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values or identifiers in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isci
    -0.08
    alic
    -0.07
    weeney
    -0.07
    duk
    -0.07
    796
    -0.07
    oke
    -0.06
     Conditional
    -0.06
    ÙĪا
    -0.06
    ugu
    -0.06
    ymb
    -0.06
    POSITIVE LOGITS
    abeth
    0.08
    zelf
    0.07
    erce
    0.07
    eker
    0.07
    è¼ī
    0.07
    essen
    0.07
    lisi
    0.06
    rement
    0.06
    quire
    0.06
    zeug
    0.06
    Act Density 0.008%

    No Known Activations