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

    Neuronpedia

    INDEX
    Explanations

    twists and unexpected developments in a narrative

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "twist" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.74
    leased
    -0.68
    pta
    -0.66
     Ducks
    -0.66
     appropriation
    -0.66
    rahim
    -0.65
    ogl
    -0.65
    league
    -0.65
     Domain
    -0.64
    inez
    -0.63
    POSITIVE LOGITS
     twist
    1.20
     twists
    1.11
     Twist
    0.89
     Whedon
    0.82
     twisting
    0.79
     weave
    0.77
     angle
    0.77
    laus
    0.74
    hered
    0.74
     stitch
    0.73
    Act Density 0.031%

    No Known Activations