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

    Neuronpedia

    INDEX
    Explanations

    mentions of blog posts

    oai_token-act-pair · gpt-3.5-turbo

    references to blog posts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ranch
    -0.88
    oko
    -0.69
    pace
    -0.69
    osph
    -0.68
    cgi
    -0.67
    untary
    -0.66
    itte
    -0.66
    urnal
    -0.66
    ulp
    -0.66
    itely
    -0.65
    POSITIVE LOGITS
     titled
    0.92
     announcing
    0.86
     entitled
    0.83
     containing
    0.77
     depicting
    0.77
     featuring
    0.76
     aimed
    0.76
     detailing
    0.72
     touting
    0.70
     summar
    0.69
    Act Density 0.278%

    No Known Activations