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

    Neuronpedia

    INDEX
    Explanations

    temporal markers and time-related vocabulary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nights
    -0.57
     Night
    -0.54
     night
    -0.54
     NIGHT
    -0.51
    night
    -0.49
    nights
    -0.49
    Night
    -0.49
     Nights
    -0.46
     NUKAT
    -0.45
    NIGHT
    -0.44
    POSITIVE LOGITS
     afternoon
    1.90
    Afternoon
    1.55
     Afternoon
    1.52
    afternoon
    1.52
     afternoons
    1.37
     Nachmittag
    1.36
     pomeriggio
    1.28
    下午
    1.16
     tarde
    1.12
    午
    0.97
    Act Density 0.178%

    No Known Activations