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

    Neuronpedia

    INDEX
    Explanations

    repetition of the word "Still"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CrossRef
    -0.85
     Vicenza
    -0.79
    __.
    -0.76
     médicaux
    -0.76
     commerciales
    -0.75
     lupo
    -0.75
     européennes
    -0.73
     wohnung
    -0.73
     agricole
    -0.72
     Erie
    -0.70
    POSITIVE LOGITS
    STILL
    1.47
     Still
    1.23
     still
    1.22
    still
    1.20
    Still
    1.18
     STILL
    1.17
     Stil
    1.10
    avía
    1.05
    stil
    1.05
     stil
    0.91
    Act Density 0.073%

    No Known Activations