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

    Neuronpedia

    INDEX
    Explanations

    questions or suggestions starting with "How about"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that pose questions or inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ö¼
    -0.86
    iple
    -0.77
    ilic
    -0.76
    Ãį
    -0.75
    lied
    -0.73
    ahl
    -0.72
    raught
    -0.72
    ilib
    -0.70
    à¼
    -0.69
    utch
    -0.69
    POSITIVE LOGITS
    !?
    0.96
    ...?
    0.94
    ?!
    0.92
    !?"
    0.86
    ?
    0.82
    ?!"
    0.79
    ?),
    0.74
     those
    0.73
    ?).
    0.71
    ?]
    0.70
    Act Density 0.040%

    No Known Activations