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

    Neuronpedia

    INDEX
    Explanations

    quotations

    oai_token-act-pair · gpt-3.5-turbo

    quotes or speech indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     festive
    -0.82
     ceremon
    -0.82
     greet
    -0.79
     delight
    -0.78
     amuse
    -0.78
     salute
    -0.78
     greeting
    -0.77
     lov
    -0.77
     commemor
    -0.76
     joy
    -0.74
    POSITIVE LOGITS
    Therefore
    1.18
     Conversely
    1.12
    Moreover
    1.12
    Furthermore
    1.07
     Moreover
    1.02
     Therefore
    1.01
    Nevertheless
    0.98
    Similarly
    0.98
     Furthermore
    0.98
     Similarly
    0.97
    Act Density 0.708%

    No Known Activations