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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships of parts to a whole

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     XK
    -0.88
     Majefty
    -0.73
     quæ
    -0.73
     Efq
    -0.73
     Laplacian
    -0.73
     pleaſure
    -0.72
     purpoſe
    -0.71
     Labrador
    -0.68
     fevere
    -0.65
     Centurion
    -0.65
    POSITIVE LOGITS
    OutOf
    1.18
     outta
    1.17
     INTO
    0.87
     Into
    0.81
     Dooley
    0.81
     the
    0.77
    ########.
    0.77
     into
    0.77
     ]];
    0.76
     vanuit
    0.73
    Act Density 0.043%

    No Known Activations