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

    Neuronpedia

    INDEX
    Explanations

    bracketed elements or lists in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    property access after bracket

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.86
    iſen
    -0.86
     houſe
    -0.85
     ainfi
    -0.84
     ſtate
    -0.83
     desmotivaciones
    -0.81
     indígen
    -0.81
     ſch
    -0.79
    ſſo
    -0.77
    setVerticalGroup
    -0.77
    POSITIVE LOGITS
    ].
    0.92
    ]->
    0.82
    ()].
    0.81
    "].
    0.80
    '].
    0.77
    ']->
    0.74
    ().
    0.73
    >().
    0.71
    */].
    0.68
    (&:
    0.68
    Act Density 0.010%

    No Known Activations