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

    Neuronpedia

    INDEX
    Explanations

    phrases or words indicating quantities or measurements, particularly regarding excessive amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.81
     propOrder
    -0.66
     Daniels
    -0.64
     Busch
    -0.63
    AnchorTagHelper
    -0.63
    useppe
    -0.62
     giang
    -0.61
    깐
    -0.61
    brainly
    -0.59
    cinnati
    -0.59
    POSITIVE LOGITS
    over
    3.99
     Over
    3.91
    Over
    3.86
     over
    3.82
     OVER
    3.45
    OVER
    3.37
    overs
    2.73
     över
    2.64
     Overs
    2.47
    オーバー
    2.41
    Act Density 0.105%

    No Known Activations