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

    Neuronpedia

    INDEX
    Explanations

    time-related words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate conditions or caveats in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĩãĤ£
    -0.85
    PDF
    -0.79
    wow
    -0.73
    Chip
    -0.71
    ONSORED
    -0.69
    blog
    -0.67
     benchmark
    -0.67
    profile
    -0.67
    leneck
    -0.65
    Screenshot
    -0.65
    POSITIVE LOGITS
     thou
    1.29
    soever
    1.25
     thence
    1.10
     ye
    1.07
     hereafter
    1.04
     mankind
    1.00
     whoever
    0.99
     notwithstanding
    0.97
     Socrates
    0.97
     Allaah
    0.95
    Act Density 0.258%

    No Known Activations