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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically commas and colons

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    471
    -0.07
    APA
    -0.07
    idan
    -0.07
     legal
    -0.06
    asive
    -0.06
    ÑĽ
    -0.06
    /hooks
    -0.06
    ãĥ¼ãĤ¸
    -0.06
    Multiply
    -0.06
    zÄħ
    -0.06
    POSITIVE LOGITS
    оже
    0.07
     lik
    0.07
    taire
    0.06
    éĢŁ
    0.06
     Roose
    0.06
     analogy
    0.06
    586
    0.06
    AUDIO
    0.06
    til
    0.06
     maybe
    0.06
    Act Density 0.068%

    No Known Activations