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

    Neuronpedia

    INDEX
    Explanations

    whitespace characters or separators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     the
    -0.64
     H
    -0.59
    </em>
    -0.58
     and
    -0.57
     OnInit
    -0.57
    
    -0.55
     (
    -0.55
    ↵
    -0.54
    vodu
    -0.53
    </h2>
    -0.52
    POSITIVE LOGITS
    expandindo
    1.01
     pleaſure
    0.86
     Jefus
    0.80
     faſt
    0.80
     lenker
    0.79
     Forumite
    0.77
     ―――――
    0.76
     leſs
    0.75
     Majefty
    0.74
    تقاوى
    0.74
    Act Density 0.311%

    No Known Activations