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

    Neuronpedia

    INDEX
    Explanations

    points of emphasis or expressions of sentiment within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    metology
    -0.56
    homonymie
    -0.55
    hysema
    -0.53
    etragen
    -0.52
     sogni
    -0.51
    leyball
    -0.50
    emia
    -0.49
     holder
    -0.49
     Diener
    -0.49
    helves
    -0.49
    POSITIVE LOGITS
    ########.
    0.80
    findpost
    0.76
     transfieras
    0.75
    ConstraintMaker
    0.68
    BASEPATH
    0.67
     trajets
    0.65
    IsContent
    0.64
    abestanden
    0.63
    awtextra
    0.62
    enumii
    0.59
    Act Density 0.057%

    No Known Activations