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

    Neuronpedia

    INDEX
    Explanations

    specific date and time combinations

    oai_token-act-pair · gpt-3.5-turbo

    numerical references to times and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bland
    -0.76
     GIF
    -0.75
     DRAG
    -0.75
    WARE
    -0.74
     BASE
    -0.72
     DISTR
    -0.72
     Debor
    -0.72
     UCH
    -0.69
     ABE
    -0.69
     DES
    -0.69
    POSITIVE LOGITS
    pm
    2.01
     pm
    1.57
    am
    1.44
    noon
    1.35
    PM
    1.35
     noon
    1.11
    AM
    1.08
     Noon
    1.08
     PM
    1.04
    hm
    1.02
    Act Density 0.029%

    No Known Activations