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

    Neuronpedia

    INDEX
    Explanations

    instances of dialogue and interactions between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    departure or abandonment

    np_acts-logits-general · gemini-2.0-flash

    leaving or exiting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.64
    Билгалдахарш
    -0.60
     surla
    -0.59
     Савезне
    -0.57
    AddTagHelper
    -0.53
     Italijanski
    -0.53
     الحره
    -0.52
     venons
    -0.52
     ſind
    -0.49
    :✨
    -0.49
    POSITIVE LOGITS
     leaving
    0.66
     leave
    0.61
     Leaving
    0.57
    Leaving
    0.56
     leaves
    0.55
     exit
    0.54
    Leave
    0.54
     disappears
    0.53
     disappearing
    0.53
     Leave
    0.52
    Act Density 0.185%

    No Known Activations