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

    Neuronpedia

    INDEX
    Explanations

    words with non-English characters and accents

    oai_token-act-pair · gpt-3.5-turbo

    specific characters or symbols that may denote special formatting or encoding issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scrut
    -0.75
     unborn
    -0.74
     mathemat
    -0.74
    enegger
    -0.73
     achie
    -0.70
     eyeb
    -0.69
     censored
    -0.68
     willpower
    -0.68
     incorpor
    -0.67
     skelet
    -0.67
    POSITIVE LOGITS
    ï¸ı
    1.12
    Ļ
    1.02
    Å
    0.97
    ģ
    0.97
    Ĩ
    0.96
    ł
    0.95
    Ľ
    0.94
    ¾
    0.94
    į
    0.91
    ¨
    0.91
    Act Density 0.038%

    No Known Activations