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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values and associative phrases in statistical or analytical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    klaim
    -0.47
    ніципа
    -0.47
     bekend
    -0.45
     even
    -0.45
     stället
    -0.44
     atuação
    -0.44
     commerciaux
    -0.42
    chok
    -0.41
    uidado
    -0.41
    不堪
    -0.41
    POSITIVE LOGITS
    StoryboardSegue
    0.92
     مشين
    0.79
     respectively
    0.78
     linkovi
    0.75
    HideFlags
    0.73
    respectively
    0.72
    ьаж
    0.71
     EconPapers
    0.71
    ConstraintMaker
    0.69
     autorytatywna
    0.69
    Act Density 0.451%

    No Known Activations