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

    Neuronpedia

    INDEX
    Explanations

    names of comic book characters and related concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ickr
    -0.76
     à¤
    -0.76
    åĮ
    -0.76
    TPPStreamerBot
    -0.75
    iscopal
    -0.71
    ï¸ı
    -0.68
    à¦
    -0.66
    à¨
    -0.66
     quake
    -0.66
     sober
    -0.65
    POSITIVE LOGITS
    canon
    1.10
     villains
    1.07
     Marvel
    1.03
     villain
    1.02
     Comics
    0.97
     Torch
    0.96
     Asgard
    0.95
     Wolverine
    0.95
     Avenger
    0.95
    buster
    0.94
    Act Density 0.234%

    No Known Activations