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

    Neuronpedia

    INDEX
    Explanations

    time stamps

    oai_token-act-pair · gpt-3.5-turbo

    time-related numeric values and timestamps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pse
    -0.84
     hig
    -0.70
    udeb
    -0.70
    ulet
    -0.69
     endors
    -0.69
     sidew
    -0.68
     tremend
    -0.67
    sole
    -0.67
     wedd
    -0.67
     hemor
    -0.64
    POSITIVE LOGITS
    Interstitial
    0.93
    PM
    0.91
    MET
    0.77
    GMT
    0.75
     IST
    0.73
    ACTED
    0.71
    OPE
    0.71
    uty
    0.70
    AM
    0.70
     PM
    0.69
    Act Density 0.059%

    No Known Activations