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

    Neuronpedia

    INDEX
    Explanations

    parentheses and numerical values in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ycin
    -0.15
    ekim
    -0.15
     Nir
    -0.15
    maze
    -0.14
    lesh
    -0.14
    veillance
    -0.14
    ÏĦÏĮ
    -0.14
    cott
    -0.14
    oux
    -0.14
    ackle
    -0.14
    POSITIVE LOGITS
    (#)
    0.17
    undles
    0.17
    .exc
    0.16
    istrovstvÃŃ
    0.14
    rowsable
    0.14
    agus
    0.14
    ÙĬÙĦØ©
    0.14
    entine
    0.14
    å¼ı
    0.14
    ITU
    0.14
    Act Density 0.010%

    No Known Activations