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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles preceded by '@'

    oai_token-act-pair · gpt-3.5-turbo

    instances of parenthetical references or handles in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icion
    -0.68
     footing
    -0.67
    itory
    -0.66
     clothes
    -0.64
    Ĥª
    -0.63
    Ļ½
    -0.63
     harms
    -0.62
    blers
    -0.61
    thin
    -0.61
    ivably
    -0.61
    POSITIVE LOGITS
    TPS
    0.95
    76561
    0.85
    ãĥİ
    0.76
    âĺ
    0.73
     Syndicate
    0.71
    eous
    0.70
    âķ
    0.70
    Beta
    0.69
    Interstitial
    0.69
     VIDEOS
    0.69
    Act Density 0.038%

    No Known Activations