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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.71
     deſt
    -0.68
     raiſ
    -0.68
     houſe
    -0.66
     ſche
    -0.66
     ſtre
    -0.65
     ſta
    -0.65
     ſever
    -0.63
    ſelf
    -0.63
    发表于
    -0.63
    POSITIVE LOGITS
    .
    0.52
     Dare
    0.48
     Lis
    0.48
     collection
    0.46
     Ser
    0.46
     Care
    0.45
     Bere
    0.45
    s
    0.44
     Kle
    0.44
     Allen
    0.44
    Act Density 0.000%

    No Known Activations