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

    Neuronpedia

    INDEX
    Explanations

    closing parentheses and other punctuation marks in function calls

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

    code method calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſtate
    -0.90
     ſch
    -0.86
     houſe
    -0.85
     myſelf
    -0.85
     juſ
    -0.84
     desmotivaciones
    -0.83
     itſelf
    -0.82
     ſche
    -0.82
     pleaſure
    -0.80
     ſtand
    -0.78
    POSITIVE LOGITS
    >().
    0.77
    ).
    0.77
    ().
    0.76
    */].
    0.76
    ').
    0.72
    (&:
    0.70
    __).
    0.69
    ()).
    0.68
    >::
    0.68
    ]').
    0.67
    Act Density 0.030%

    No Known Activations