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

    Neuronpedia

    INDEX
    Explanations

    significant keywords and variables in scientific or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egasus
    -0.15
    anga
    -0.15
    609
    -0.14
    ÙĤات
    -0.14
    ichten
    -0.14
    tings
    -0.14
    armor
    -0.13
    agas
    -0.13
    iska
    -0.13
     kicks
    -0.13
    POSITIVE LOGITS
    antino
    0.15
    oje
    0.15
    üzel
    0.14
     Proud
    0.14
     Tall
    0.14
    lify
    0.14
    _OVERRIDE
    0.13
    errupt
    0.13
    ustil
    0.13
    dea
    0.13
    Act Density 0.002%

    No Known Activations