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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically parentheses and closing marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iates
    -0.72
    ilee
    -0.67
    ework
    -0.66
     eyeb
    -0.65
     deleg
    -0.64
    itiz
    -0.63
    yright
    -0.63
     cohesion
    -0.61
     yourselves
    -0.61
     mort
    -0.61
    POSITIVE LOGITS
    âķ
    0.85
    20439
    0.78
    ï¸
    0.78
    âķIJ
    0.77
    Fri
    0.75
    RESULTS
    0.73
    è¦ļéĨĴ
    0.71
    RANT
    0.68
     Runs
    0.66
    TN
    0.66
    Act Density 0.091%

    No Known Activations