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

    Neuronpedia

    INDEX
    Explanations

    references or mentions of hints or clues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Modèle
    -0.69
     kona
    -0.62
     Diction
    -0.61
     Equipe
    -0.59
     Ouv
    -0.59
     Équipe
    -0.58
     médic
    -0.57
     Chambres
    -0.57
     Dimen
    -0.56
    Imaginary
    -0.56
    POSITIVE LOGITS
     hint
    1.40
     hints
    1.29
    hint
    1.16
     clue
    1.15
     clues
    1.09
     hinting
    1.08
     hinted
    1.02
    Hint
    0.99
    hints
    0.95
     Hint
    0.95
    Act Density 0.086%

    No Known Activations