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

    Neuronpedia

    INDEX
    Explanations

    numerical statistics related to sports performance

    oai_token-act-pair · gpt-3.5-turbo

    opening parentheses in statistical or score-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     antim
    -0.81
     wre
    -0.80
     lull
    -0.73
     fres
    -0.72
     hiding
    -0.70
     artisan
    -0.70
     tremend
    -0.69
     antiv
    -0.68
     terr
    -0.68
    osate
    -0.68
    POSITIVE LOGITS
    including
    1.17
    excluding
    1.17
    which
    1.16
    formerly
    1.15
    although
    1.11
    both
    1.11
    also
    1.11
    via
    1.10
    pictured
    1.08
    mostly
    1.08
    Act Density 0.107%

    No Known Activations