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

    Neuronpedia

    INDEX
    Explanations

    links or mentions of subscribing to newsletters

    oai_token-act-pair · gpt-3.5-turbo

    instances of newsletter-related content and calls to action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aimon
    -0.71
    gart
    -0.67
    aukee
    -0.67
    burgh
    -0.66
     Harrington
    -0.63
    uyomi
    -0.62
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.62
     biome
    -0.59
    footed
    -0.59
     Bald
    -0.58
    POSITIVE LOGITS
    Prev
    0.78
    ource
    0.77
    ̶
    0.73
    push
    0.68
     Cancel
    0.68
    interstitial
    0.68
    \/
    0.67
    raper
    0.67
    ince
    0.66
    encer
    0.65
    Act Density 0.073%

    No Known Activations