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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and delimiters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     similarly
    -0.77
    同じく
    -0.72
     Similarly
    -0.71
     secondly
    -0.69
     firstly
    -0.66
    同様に
    -0.65
     entweder
    -0.64
     subsequent
    -0.64
     either
    -0.64
    Similarly
    -0.63
    POSITIVE LOGITS
     tudo
    1.27
    etc
    1.12
    Bref
    1.08
     etc
    1.08
     allemaal
    1.08
     Etc
    1.07
    总之
    1.07
    などなど
    1.05
    这一切
    1.05
    Etc
    1.02
    Act Density 0.293%

    No Known Activations