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

    Neuronpedia

    INDEX
    Explanations

    intensifiers that emphasize emotions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.63
    براير
    -0.60
    żeli
    -0.58
     nakalista
    -0.57
    .*")]
    -0.57
     ['./
    -0.56
    ásban
    -0.54
    gulier
    -0.54
    asztal
    -0.53
    oges
    -0.53
    POSITIVE LOGITS
     damn
    0.83
     darn
    0.80
     so
    0.78
     freaking
    0.74
     damned
    0.70
     goddamn
    0.68
     freakin
    0.68
     unbelievably
    0.66
     fucking
    0.63
     amazing
    0.63
    Act Density 0.065%

    No Known Activations