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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals or groups in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wick
    -0.17
    ascript
    -0.16
    hausen
    -0.15
     SOS
    -0.15
    _simps
    -0.15
    eldon
    -0.15
    аниÑĨ
    -0.15
    nick
    -0.15
    _stylesheet
    -0.14
     ele
    -0.14
    POSITIVE LOGITS
    UCH
    0.18
    eten
    0.15
    arts
    0.15
    uch
    0.15
    ora
    0.15
     Lehr
    0.15
    atti
    0.15
    lore
    0.14
    orum
    0.14
     Arts
    0.14
    Act Density 0.026%

    No Known Activations