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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and structural elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oman
    -0.16
    orman
    -0.16
    mlin
    -0.15
     Tat
    -0.15
    ivec
    -0.15
     Norman
    -0.15
    Normalized
    -0.15
    lict
    -0.14
    ORMAT
    -0.14
    enser
    -0.14
    POSITIVE LOGITS
    sville
    0.17
    arra
    0.17
    igkeit
    0.15
    du
    0.15
    ures
    0.14
    дон
    0.14
    chop
    0.14
    άκ
    0.14
    oui
    0.14
    ier
    0.14
    Act Density 0.011%

    No Known Activations