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

    Neuronpedia

    INDEX
    Explanations

    abbreviations or acronyms followed by the number 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    references to Collaborative Consumption (often abbreviated as "CC")

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĦ
    -0.80
    onymous
    -0.79
    strument
    -0.78
    ãĤ¯
    -0.74
    selves
    -0.74
    velt
    -0.72
    ãĤ¶
    -0.71
    wered
    -0.68
     Ghostbusters
    -0.67
     Roosevelt
    -0.66
    POSITIVE LOGITS
    ombat
    0.96
    CCC
    0.96
    entric
    0.93
    CC
    0.92
    ORD
    0.91
    ADA
    0.91
    arthy
    0.89
    lean
    0.87
    inelli
    0.86
    ESS
    0.84
    Act Density 0.009%

    No Known Activations