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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate confusion or hesitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adaptiveStyles
    -0.63
    ècie
    -0.60
     Савезне
    -0.60
    ftagPool
    -0.55
     المعيارى
    -0.53
     Administrativna
    -0.53
    WebElementEntity
    -0.52
     iNdEx
    -0.52
    ➟
    -0.49
    يكب
    -0.49
    POSITIVE LOGITS
     initially
    3.34
     initial
    3.05
     Initially
    2.91
    Initially
    2.88
     inicialmente
    2.63
    initial
    2.61
     anfangs
    2.55
    Initial
    2.53
     Initial
    2.47
     inicial
    2.34
    Act Density 1.133%

    No Known Activations