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

    Neuronpedia

    INDEX
    Explanations

    references and mentions of citations needed in text

    oai_token-act-pair · gpt-3.5-turbo

    instances of citation or references within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olen
    -0.77
    antle
    -0.70
    chest
    -0.67
     saline
    -0.61
    oz
    -0.60
     cosmetic
    -0.59
    rop
    -0.59
    rame
    -0.58
     unin
    -0.57
     Meadow
    -0.57
    POSITIVE LOGITS
     Citation
    0.93
    itation
    0.92
     citation
    0.84
    itations
    0.83
     quotes
    0.76
     thereof
    0.74
    itating
    0.72
    itates
    0.71
    ...]
    0.71
    itated
    0.69
    Act Density 0.013%

    No Known Activations