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

    Neuronpedia

    INDEX
    Explanations

    repetitive phrases indicating frequency or recurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lilli
    -0.67
     Orto
    -0.59
     flotte
    -0.59
     porcelaine
    -0.58
     Dest
    -0.58
    rowa
    -0.58
     Makoto
    -0.56
    itettura
    -0.56
    Huhu
    -0.55
    Dest
    -0.55
    POSITIVE LOGITS
    Twice
    1.03
     Twice
    0.99
    twice
    0.98
     TWICE
    0.97
     twice
    0.95
    RenderAtEndOf
    0.93
     thrice
    0.88
     MainAxisSize
    0.85
     zweimal
    0.80
    AutoScaleMode
    0.79
    Act Density 0.095%

    No Known Activations