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

    Neuronpedia

    INDEX
    Explanations

    timestamps in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    numerical data relevant to timestamps and possibly dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hemor
    -0.80
     pse
    -0.78
     tremend
    -0.73
     nomine
    -0.69
     looph
    -0.69
     endors
    -0.68
     nodd
    -0.67
     unaff
    -0.66
     ingred
    -0.65
     soared
    -0.65
    POSITIVE LOGITS
    Interstitial
    0.83
    ACTED
    0.78
    PM
    0.75
    MET
    0.73
    aretz
    0.71
    Ur
    0.69
    0100
    0.68
    uty
    0.67
    oak
    0.67
    âĢ¦]
    0.66
    Act Density 0.078%

    No Known Activations