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

    Neuronpedia

    INDEX
    Explanations

    the word "excuse" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    the word "excuse" and its variations, typically in contexts involving justifications or rationalizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acid
    -0.87
    yss
    -0.87
    itals
    -0.85
    duino
    -0.78
    atform
    -0.77
    iking
    -0.74
    tein
    -0.73
    ipeg
    -0.73
    utenberg
    -0.72
    weeney
    -0.72
    POSITIVE LOGITS
     excuse
    1.20
     excuses
    1.16
     explanations
    0.90
     justifying
    0.87
     WHY
    0.85
     why
    0.84
     explanation
    0.83
     justification
    0.79
    abl
    0.79
     explaining
    0.79
    Act Density 0.034%

    No Known Activations