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

    Neuronpedia

    INDEX
    Explanations

    phrases that include special characters typically not found in regular English text, most likely related to programming or data formatting

    oai_token-act-pair · gpt-3.5-turbo

    instances of an unusual character or symbol in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    worms
    -0.79
     commun
    -0.75
    ieth
    -0.71
    ruck
    -0.68
    aimon
    -0.68
    perate
    -0.67
    ordinate
    -0.66
    erald
    -0.66
    iard
    -0.64
    ides
    -0.64
    POSITIVE LOGITS
    ————————
    1.82
    ————
    1.79
    ————————————————
    1.25
    ——
    1.00
    _-
    0.84
     albeit
    0.81
     namely
    0.76
    especially
    0.73
    feat
    0.73
    albeit
    0.72
    Act Density 0.119%

    No Known Activations