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

    Neuronpedia

    INDEX
    Explanations

    references to video games and fictional characters with superhero-like or fantastical elements

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ashtra
    -0.93
    »Ĵ
    -0.88
    uscript
    -0.71
    marg
    -0.71
    acca
    -0.70
    auga
    -0.70
    etheless
    -0.67
    iland
    -0.67
    ĻĤ
    -0.67
    cdn
    -0.66
    POSITIVE LOGITS
     Duty
    0.75
     Cube
    0.70
    Vision
    0.65
     arms
    0.65
    izard
    0.62
     Cthulhu
    0.61
     wake
    0.60
     Ju
    0.60
     Conquer
    0.60
     Ware
    0.60
    Act Density 10.910%

    No Known Activations