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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks indicating pauses or breaks in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otherwise
    -0.17
     hence
    -0.16
    oven
    -0.16
     pronto
    -0.15
     lately
    -0.15
    oise
    -0.15
    Callbacks
    -0.15
    .now
    -0.15
    dash
    -0.14
     OTHERWISE
    -0.14
    POSITIVE LOGITS
     we
    0.19
     after
    0.18
     there
    0.16
     it
    0.16
     however
    0.15
     thanks
    0.15
     though
    0.15
    为äºĨ
    0.15
    mozilla
    0.15
     nhá»Ŀ
    0.14
    Act Density 0.143%

    No Known Activations