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

    Neuronpedia

    INDEX
    Explanations

    phrases related to memories or realizations

    oai_token-act-pair · gpt-3.5-turbo

    thoughts or ideas that stand out prominently in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reliance
    -0.74
    ardless
    -0.73
    partial
    -0.68
     stewards
    -0.68
     subcontract
    -0.64
     incompet
    -0.63
    ymm
    -0.63
    æ©Ł
    -0.63
     incompetent
    -0.62
     subsistence
    -0.62
    POSITIVE LOGITS
     whispered
    0.89
     me
    0.83
     etched
    0.80
     my
    0.80
     dawn
    0.78
    dream
    0.74
     clicked
    0.73
     occurred
    0.72
     flashed
    0.72
     aloud
    0.72
    Act Density 0.373%

    No Known Activations