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

    Neuronpedia

    INDEX
    Explanations

    unexpected developments or surprises in a narrative sequence

    oai_token-act-pair · gpt-3.5-turbo

    references to unexpected developments or plot twists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.75
    leased
    -0.70
    hammad
    -0.69
    asking
    -0.68
    rahim
    -0.67
    estine
    -0.65
     Defenders
    -0.63
     appropriation
    -0.62
     Ducks
    -0.62
    league
    -0.62
    POSITIVE LOGITS
     twist
    1.15
     twists
    1.10
     Twist
    0.89
     endings
    0.80
     Whedon
    0.77
     twisting
    0.75
     weave
    0.74
     helic
    0.73
    abouts
    0.73
     angle
    0.70
    Act Density 0.032%

    No Known Activations