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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence of spokespersons and press releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tier
    -0.20
    Tier
    -0.15
    оди
    -0.14
    idon
    -0.14
    ÙĨاÙĨ
    -0.14
    wed
    -0.14
    enstein
    -0.14
    Express
    -0.14
    ÅĪ
    -0.14
    _initialize
    -0.14
    POSITIVE LOGITS
    aversable
    0.15
    ỳ
    0.15
    .Navigator
    0.15
    legg
    0.15
    Ñĸдно
    0.15
    ulfilled
    0.14
    ripper
    0.14
    adx
    0.14
     Randall
    0.14
    PEAT
    0.14
    Act Density 0.073%

    No Known Activations