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

    Neuronpedia

    INDEX
    Explanations

    terms related to various topics such as comic books, science fiction movies, marathons, political figures, Hollywood studios, sports, and culinary flavors

    oai_token-act-pair · gpt-3.5-turbo

    references to specific genres and characteristics of films and storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.80
    çĶ°
    -0.74
    é¾į
    -0.72
     LIMITED
    -0.63
    YES
    -0.63
     jointly
    -0.61
     Ezek
    -0.60
     Qiao
    -0.60
     Annotations
    -0.59
    FORE
    -0.59
    POSITIVE LOGITS
     anymore
    1.18
     nor
    1.05
     dystop
    0.77
    agra
    0.77
     or
    0.75
     gimmick
    0.73
     fairy
    0.72
     guy
    0.72
     pony
    0.71
    iche
    0.71
    Act Density 0.671%

    No Known Activations