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

    Neuronpedia

    INDEX
    Explanations

    justifications for infidelity and the excuses people make for cheating

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icari
    -0.17
     Maiden
    -0.15
    USART
    -0.15
    ActionResult
    -0.15
    aldi
    -0.15
    alah
    -0.15
    asher
    -0.14
    lein
    -0.14
    anki
    -0.14
    atta
    -0.14
    POSITIVE LOGITS
     arguments
    0.35
     argument
    0.34
     Arguments
    0.31
    argument
    0.29
     Argument
    0.29
     excuse
    0.28
    arguments
    0.28
    Argument
    0.26
     excuses
    0.24
    Arguments
    0.23
    Act Density 0.276%

    No Known Activations