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

    Neuronpedia

    INDEX
    Explanations

    references to specific times and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nights
    -0.76
     nights
    -0.74
    Nights
    -0.71
     nachts
    -0.68
     nightly
    -0.67
     nacht
    -0.66
     Nacht
    -0.66
    Night
    -0.65
     nocturne
    -0.65
     nuit
    -0.65
    POSITIVE LOGITS
     afternoon
    1.50
     lunch
    1.31
     noon
    1.31
     Afternoon
    1.21
     midday
    1.20
    afternoon
    1.20
     Lunch
    1.19
    Afternoon
    1.18
    lunch
    1.18
    Lunch
    1.15
    Act Density 0.100%

    No Known Activations