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

    Neuronpedia

    INDEX
    Explanations

    statements or remarks made by individuals in a text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of statements, comments, and remarks made by individuals or officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ategory
    -0.76
     ILCS
    -0.75
    ccording
    -0.66
    minster
    -0.63
    everal
    -0.63
     veter
    -0.62
    ordinate
    -0.62
    rollers
    -0.61
     hemor
    -0.61
    HAM
    -0.61
    POSITIVE LOGITS
    oids
    0.85
     echoed
    0.77
     regarding
    0.73
    fulness
    0.71
     illustrates
    0.69
     spree
    0.69
     notwithstanding
    0.69
     coincides
    0.68
    ings
    0.68
     ACTIONS
    0.68
    Act Density 0.193%

    No Known Activations