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

    Neuronpedia

    INDEX
    Explanations

    phrases related to cutting or removing parts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -0.75
     kasarigan
    -0.75
    Rujuakan
    -0.68
    ьаж
    -0.64
     ―――――
    -0.64
     iNdEx
    -0.63
     Majefty
    -0.63
    Халык
    -0.62
    RegressionTest
    -0.61
     Diſ
    -0.61
    POSITIVE LOGITS
     cut
    0.77
     CUT
    0.68
     Cuts
    0.67
     cuts
    0.67
     Cut
    0.66
     cutters
    0.66
     cutting
    0.62
    Cut
    0.62
    Cuts
    0.61
    cut
    0.60
    Act Density 0.278%

    No Known Activations