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

    Neuronpedia

    INDEX
    Explanations

    elements related to user interface components and their styling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “
    -0.69
    ništvo
    -0.63
     gynhyrchwyd
    -0.61
    发表于
    -0.61
     ModelExpression
    -0.60
    ,
    -0.60
    ↵↵
    -0.59
    <eos>
    -0.59
    RTLD
    -0.58
     and
    -0.57
    POSITIVE LOGITS
     Efq
    0.67
    ……"
    0.64
     Мексичка
    0.64
     AppBundle
    0.63
     Athen
    0.63
     Anſ
    0.62
     Pind
    0.61
     Shakspeare
    0.61
     Verſ
    0.61
     Shaksp
    0.60
    Act Density 0.071%

    No Known Activations