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

    Neuronpedia

    INDEX
    Explanations

    differences or inconsistencies in text data, such as incorrect subtitles, disputed authorship, adjusted stats, and validation formats

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Rh
    -0.67
     Adin
    -0.66
     Chero
    -0.66
    Kn
    -0.62
     Hungry
    -0.62
     Smy
    -0.61
     Rhod
    -0.61
    lly
    -0.60
     Blind
    -0.59
    Ash
    -0.59
    POSITIVE LOGITS
     program
    0.79
     programme
    0.76
     procedure
    0.76
     system
    0.71
     scenario
    0.69
     category
    0.69
     ensemble
    0.69
     lineup
    0.67
     sequence
    0.67
     stat
    0.67
    Act Density 27.149%

    No Known Activations