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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formality in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Neutral
    -0.15
    ög
    -0.14
    pector
    -0.14
     Neutral
    -0.14
    lernen
    -0.14
    argo
    -0.14
    hic
    -0.14
    oser
    -0.14
    ollision
    -0.13
     Wort
    -0.13
    POSITIVE LOGITS
    359
    0.15
    ayer
    0.15
    aturas
    0.15
     seedu
    0.15
    ature
    0.15
    moid
    0.14
     Rudd
    0.14
    odash
    0.14
    87
    0.14
    URLRequest
    0.14
    Act Density 0.000%

    No Known Activations