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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating rankings or positions, particularly related to the term "top."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    umpf
    -0.72
    twimg
    -0.69
    SequentialGroup
    -0.67
     whiteColor
    -0.67
     Мексичка
    -0.65
    bellar
    -0.64
    iculous
    -0.63
    entennial
    -0.62
    lty
    -0.60
     bronco
    -0.59
    POSITIVE LOGITS
     quæ
    0.72
     busiest
    0.62
    quatre
    0.61
     faveur
    0.60
     FAVORITE
    0.59
     hvě
    0.58
     principali
    0.57
    favourite
    0.57
     Vina
    0.57
    fav
    0.56
    Act Density 0.009%

    No Known Activations