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

    Neuronpedia

    INDEX
    Explanations

    special characters and punctuation in a scientific or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     �
    -0.80
    AndEndTag
    -0.79
    dür
    -0.76
     conci
    -0.71
    LOGGER
    -0.68
     ´
    -0.66
     Bø
    -0.66
     ``
    -0.64
    pertino
    -0.64
    %)$
    -0.63
    POSITIVE LOGITS
    ————————
    1.15
    ————————————————
    1.14
    ———
    1.02
     —
    1.01
    ————
    0.99
    —————
    0.97
    ly
    0.93
    ——————
    0.91
     —,
    0.85
    ]^
    0.84
    Act Density 0.629%

    No Known Activations