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

    Neuronpedia

    INDEX
    Explanations

    greetings and welcomes in text

    oai_token-act-pair · gpt-3.5-turbo

    the presence of punctuation marks, particularly commas and exclamation points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ___
    -0.76
    odo
    -0.70
    Nonetheless
    -0.70
    enger
    -0.67
    Others
    -0.67
    Parameters
    -0.67
    odes
    -0.65
    endish
    -0.63
    amount
    -0.62
    ei
    -0.62
    POSITIVE LOGITS
     featuring
    1.05
     showcasing
    0.95
     aka
    0.93
     wherein
    0.92
     where
    0.90
     LLC
    0.88
    feat
    0.87
     courtesy
    0.84
     Featuring
    0.83
     Inc
    0.78
    Act Density 0.297%

    No Known Activations