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

    Neuronpedia

    INDEX
    Explanations

    statements relating to financial amounts

    oai_token-act-pair · gpt-3.5-turbo

    sentences ending with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     deserts
    -0.72
     stubborn
    -0.71
     challeng
    -0.68
     advanced
    -0.67
     millisec
    -0.65
     dynamically
    -0.65
     regener
    -0.65
     everywhere
    -0.64
     rigorous
    -0.64
     robust
    -0.63
    POSITIVE LOGITS
     PHOTO
    1.03
     However
    1.01
     Officials
    1.00
     He
    0.97
     Photograph
    0.97
     Photo
    0.95
     Hide
    0.95
     REUTERS
    0.94
     Others
    0.93
     She
    0.92
    Act Density 0.413%

    No Known Activations