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

    Neuronpedia

    INDEX
    Explanations

    keywords related to technical instructions or coding like asterisks "*", email, and percentage values

    oai_token-act-pair · gpt-3.5-turbo

    instances of asterisks or related formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eness
    -0.79
    adelphia
    -0.78
    ichick
    -0.75
    ilitarian
    -0.70
    omorphic
    -0.70
    inelli
    -0.69
    ivated
    -0.68
    kson
    -0.68
    rolet
    -0.68
     extinction
    -0.67
    POSITIVE LOGITS
    âĢ¢âĢ¢
    1.00
    AUT
    0.91
    SK
    0.90
    NEW
    0.85
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.85
    Insert
    0.84
    insert
    0.83
    ERROR
    0.82
    laughs
    0.79
    execute
    0.79
    Act Density 0.015%

    No Known Activations