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

    Neuronpedia

    INDEX
    Explanations

    time-related expressions or time of occurrence

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate approximations of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.67
    qua
    -0.65
     Written
    -0.59
    ple
    -0.58
    eming
    -0.58
     DRAG
    -0.57
    BLE
    -0.57
    herty
    -0.56
    inen
    -0.56
    ysis
    -0.56
    POSITIVE LOGITS
    clock
    0.91
     midday
    0.87
     1900
    0.83
     midnight
    0.79
     dozen
    0.78
     noon
    0.76
     corners
    0.76
     1400
    0.76
     9000
    0.75
     1600
    0.74
    Act Density 0.042%

    No Known Activations