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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks that indicate a list or separation of clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ught
    -0.85
    gow
    -0.73
    reated
    -0.73
    ined
    -0.65
    sein
    -0.64
    vey
    -0.64
    oons
    -0.63
    pec
    -0.62
    lean
    -0.62
    cius
    -0.62
    POSITIVE LOGITS
     albeit
    1.01
     culminating
    0.91
     however
    0.88
     but
    0.87
     prompting
    0.86
     although
    0.81
     resulting
    0.80
     except
    0.79
     indicating
    0.79
     replaced
    0.78
    Act Density 0.359%

    No Known Activations