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

    Neuronpedia

    INDEX
    Explanations

    superlative phrases indicating the highest degree of quality or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     becauſe
    -0.69
     poffible
    -0.68
     pleaſure
    -0.68
     itſelf
    -0.67
     Anſ
    -0.66
     reafon
    -0.66
     roundabout
    -0.65
     clerical
    -0.65
     slutt
    -0.64
     Thebes
    -0.64
    POSITIVE LOGITS
     most
    0.80
     Most
    0.68
     TextAlign
    0.61
     FetchType
    0.59
    Most
    0.59
     MatDialog
    0.59
    DOCTYPE
    0.59
    most
    0.55
     deemed
    0.54
     MOST
    0.54
    Act Density 0.154%

    No Known Activations