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

    Neuronpedia

    INDEX
    Explanations

    specific punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically semicolons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ¥µ
    -0.87
    omorphic
    -0.76
    ema
    -0.73
    rio
    -0.71
    din
    -0.70
    se
    -0.69
    ero
    -0.68
    odes
    -0.68
    ħĭ
    -0.67
    senal
    -0.66
    POSITIVE LOGITS
     furthermore
    0.94
     thence
    0.94
     alternatively
    0.91
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.88
    -)
    0.88
     moreover
    0.85
     Flavoring
    0.85
     meanwhile
    0.81
    âĢ¢âĢ¢
    0.80
     };
    0.79
    Act Density 0.043%

    No Known Activations