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

    Neuronpedia

    INDEX
    Explanations

    active descriptions of media or entertainment, particularly focusing on elements that impact the storytelling or character dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     truly
    -0.18
     Truly
    -0.17
     literally
    -0.16
     Absolutely
    -0.15
    Absolutely
    -0.14
    æĽ´åĬł
    -0.14
     absolute
    -0.14
    ialis
    -0.14
     literal
    -0.14
     absolutely
    -0.14
    POSITIVE LOGITS
     decent
    0.50
     reasonably
    0.43
     reasonable
    0.40
     fairly
    0.39
    reasonable
    0.35
     pretty
    0.35
    pretty
    0.33
     nice
    0.31
     respectable
    0.30
     khá
    0.29
    Act Density 0.713%

    No Known Activations