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

    Neuronpedia

    INDEX
    Explanations

    phrases that evaluate performance and creativity in artistic works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ClientSize
    -0.52
    KommentareTeilen
    -0.52
     prétend
    -0.48
    Étape
    -0.47
    complexType
    -0.47
     mauvaise
    -0.47
     allegedly
    -0.47
    
    -0.46
     notorious
    -0.46
     peor
    -0.46
    POSITIVE LOGITS
     deft
    1.13
     skillfully
    1.08
     expertly
    0.97
     skillful
    0.89
     masterful
    0.86
     skilful
    0.85
     flawlessly
    0.85
     superbly
    0.83
     skil
    0.83
     brilliantly
    0.81
    Act Density 0.338%

    No Known Activations