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

    Neuronpedia

    INDEX
    Explanations

    phrases that express surprises or unexpected outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portail
    -0.86
    :✨
    -0.83
    SourceChecksum
    -0.71
     архивлан
    -0.68
     orizz
    -0.65
    matchCondition
    -0.65
     CreateTagHelper
    -0.64
     سكانية
    -0.64
    Xna
    -0.64
     kasarigan
    -0.64
    POSITIVE LOGITS
     understandably
    0.84
     rightly
    0.64
     rightfully
    0.64
     unsur
    0.61
    prisingly
    0.60
     understandable
    0.57
     terecht
    0.56
    ArgsConstructor
    0.55
    难怪
    0.55
    Naturally
    0.53
    Act Density 0.215%

    No Known Activations