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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "out" or its associated phrases related to performance and rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    outperforming or exceeding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.46
    IBOutlet
    -0.46
     indígen
    -0.45
    Hentet
    -0.44
     trenes
    -0.41
    Invariant
    -0.40
     turística
    -0.39
     المعيارى
    -0.39
    DidLoad
    -0.39
     vacío
    -0.39
    POSITIVE LOGITS
     surpass
    0.61
     outnumbered
    0.61
     surpassed
    0.61
     exceed
    0.60
     outweigh
    0.60
     outperform
    0.59
     surpasses
    0.57
     exceeded
    0.54
     exceeds
    0.52
     superior
    0.51
    Act Density 0.043%

    No Known Activations