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

    Neuronpedia

    INDEX
    Explanations

    phrases related to academic research and publications

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to research, development, and scholarly discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.88
    Ö¼
    -0.73
    NESS
    -0.71
     ¯
    -0.68
    nery
    -0.66
    00007
    -0.64
    rin
    -0.60
    ridor
    -0.59
    1001
    -0.59
    ISION
    -0.58
    POSITIVE LOGITS
     varying
    0.98
     various
    0.95
    compan
    0.80
     differing
    0.78
     disparate
    0.75
     faiths
    0.75
     different
    0.75
     ranging
    0.73
     portfolios
    0.72
     settlements
    0.72
    Act Density 0.590%

    No Known Activations