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

    Neuronpedia

    INDEX
    Explanations

    negative assertions or denials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AutoScaleMode
    -0.81
     odkazy
    -0.59
     lenker
    -0.57
    imakasih
    -0.54
     disambiguazione
    -0.54
    therosclerosis
    -0.53
    contentLoaded
    -0.52
     Semoga
    -0.52
     alternately
    -0.52
     kasarigan
    -0.52
    POSITIVE LOGITS
     sure
    0.67
     going
    0.61
     suppose
    0.59
     supposed
    0.58
     familiar
    0.58
     gonna
    0.55
     even
    0.55
    }());
    0.52
    AddTagHelper
    0.50
     kidding
    0.49
    Act Density 0.096%

    No Known Activations