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

    Neuronpedia

    INDEX
    Explanations

    phrases related to news reports and ongoing discussions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to media reporting and coverage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     superiors
    -0.68
     Alone
    -0.68
    aterasu
    -0.67
    cko
    -0.60
     outnumbered
    -0.59
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.59
    ggies
    -0.58
     boss
    -0.58
     accountant
    -0.57
    ibles
    -0.57
    POSITIVE LOGITS
     lately
    1.16
     recent
    0.90
     discussion
    0.85
     regarding
    0.83
     commentary
    0.83
     theor
    0.83
    published
    0.82
     speculation
    0.81
     concerning
    0.81
     largeDownload
    0.79
    Act Density 0.485%

    No Known Activations