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

    Neuronpedia

    INDEX
    Explanations

    segments or sections of structured text typical in scientific or technical documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     iſt
    -1.48
     purpoſe
    -1.43
     itſelf
    -1.39
     مرئيه
    -1.35
     myſelf
    -1.34
    脚注の使い方
    -1.33
     ſind
    -1.31
     pleaſure
    -1.28
     raiſ
    -1.27
     ―――――
    -1.27
    POSITIVE LOGITS
     
    0.93
    ↵
    0.90
    ↵↵
    0.83
    .
    0.73
    1
    0.70
    ?
    0.69
    3
    0.68
     (
    0.66
    </h2>
    0.64
    2
    0.63
    Act Density 0.402%

    No Known Activations