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

    Neuronpedia

    INDEX
    Explanations

    sentences with punctuation and structured patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Infatti
    -0.94
    むしろ
    -0.87
     infatti
    -0.83
     sogar
    -0.80
     Apalagi
    -0.80
     even
    -0.77
    even
    -0.75
     zelfs
    -0.73
    Especially
    -0.72
     addirittura
    -0.72
    POSITIVE LOGITS
    出版年
    0.67
     Within
    0.66
     Upon
    0.64
     upon
    0.63
    Naturally
    0.63
     للاسماء
    0.63
     during
    0.62
    during
    0.62
    Within
    0.61
    Upon
    0.60
    Act Density 0.554%

    No Known Activations