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

    Neuronpedia

    INDEX
    Explanations

    punctuation and sentence structures in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Whilst
    -0.17
    Util
    -0.17
     jedoch
    -0.17
    ÑģÑĤÑĢÑĥ
    -0.16
    ilst
    -0.16
     whilst
    -0.16
     Lets
    -0.15
    óz
    -0.15
    Lets
    -0.15
    ü
    -0.14
    POSITIVE LOGITS
     And
    0.18
    Asked
    0.16
     Asked
    0.16
     ("
    0.16
    malink
    0.15
     amid
    0.14
    [*
    0.14
     ,,
    0.14
     Nor
    0.14
     "
    0.14
    Act Density 0.485%

    No Known Activations