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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks or specific symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wich
    -0.14
    ocity
    -0.14
     besides
    -0.13
    ensibly
    -0.13
     Various
    -0.13
     regardless
    -0.13
    lee
    -0.13
     Both
    -0.13
     which
    -0.13
    Nice
    -0.13
    POSITIVE LOGITS
     yet
    0.31
    yet
    0.21
     albeit
    0.21
    Yet
    0.20
     Yet
    0.20
     often
    0.15
     wenn
    0.15
     nay
    0.15
    undi
    0.15
    anza
    0.15
    Act Density 0.074%

    No Known Activations