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

    Neuronpedia

    INDEX
    Explanations

    characters representing code syntax

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of backtick characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢ²
    -0.92
    "âĢ¦
    -0.86
    "—
    -0.79
    âĢ¦
    -0.77
    )—
    -0.76
    ´
    -0.74
    Advertisements
    -0.74
    âĢ³
    -0.73
    cia
    -0.73
    —-
    -0.72
    POSITIVE LOGITS
     `
    3.32
     �
    2.33
     ``
    2.23
     \"
    1.57
     |--
    1.53
     ``(
    1.39
     ����
    1.30
     [[
    1.28
    ``
    1.27
    .�
    1.27
    Act Density 0.018%

    No Known Activations