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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and special characters

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks that indicate the end of a sentence or important phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reincarnated
    -0.72
     sacked
    -0.69
     pursued
    -0.68
     consumed
    -0.67
     dissu
    -0.65
     engulfed
    -0.64
     lifes
    -0.63
     ejected
    -0.63
     sacrificed
    -0.62
     shielded
    -0.62
    POSITIVE LOGITS
    Interview
    1.00
    ccording
    0.96
    Specifically
    0.92
    Writing
    0.89
    Discussion
    0.87
    Talking
    0.84
    RESULTS
    0.84
    Pages
    0.83
    TABLE
    0.83
    Reading
    0.82
    Act Density 0.631%

    No Known Activations