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

    Neuronpedia

    INDEX
    Explanations

    editorial notes or comments from an editor

    oai_token-act-pair · gpt-3.5-turbo

    references to editorial notes or authors within the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pered
    -0.70
     Vulcan
    -0.69
     Antar
    -0.67
    omething
    -0.67
    fw
    -0.66
    avid
    -0.65
    lda
    -0.64
     turtles
    -0.64
    ought
    -0.64
     Sicily
    -0.63
    POSITIVE LOGITS
    ial
    0.91
    ials
    0.90
    ially
    0.86
    furt
    0.81
    ror
    0.76
    GUI
    0.74
    ienne
    0.73
    Editor
    0.73
    ickson
    0.73
    iversary
    0.72
    Act Density 0.019%

    No Known Activations