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

    Neuronpedia

    INDEX
    Explanations

    sections of text within square brackets

    oai_token-act-pair · gpt-3.5-turbo

    brackets and their usage in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edIn
    -0.72
    oke
    -0.71
    wagen
    -0.71
    rame
    -0.71
    seys
    -0.70
    merce
    -0.69
    mable
    -0.69
    emouth
    -0.68
     pens
    -0.64
    berra
    -0.64
    POSITIVE LOGITS
     edit
    1.30
    ËĪ
    1.27
    ?]
    1.25
    Pg
    1.07
    Footnote
    0.98
    !]
    0.97
    :]
    0.93
    ...]
    0.93
    emphasis
    0.92
    via
    0.89
    Act Density 0.029%

    No Known Activations