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

    Neuronpedia

    INDEX
    Explanations

    technical and specific formatting elements

    oai_token-act-pair · gpt-3.5-turbo

    statements that introduce or caption visual elements such as images or videos

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     organis
    -0.81
     foc
    -0.76
     emancipation
    -0.71
     organised
    -0.71
     endeavour
    -0.71
     organising
    -0.70
     annex
    -0.69
     preferred
    -0.69
     insured
    -0.69
     sulph
    -0.68
    POSITIVE LOGITS
    https
    1.43
    http
    1.28
    Notice
    1.20
    Screenshot
    1.13
    Yep
    1.11
    Courtesy
    1.08
    Looks
    1.05
    Advertisement
    1.04
    Feature
    1.04
    UPDATE
    0.99
    Act Density 0.251%

    No Known Activations