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

    Neuronpedia

    INDEX
    Explanations

    technology-related terms and features

    oai_token-act-pair · gpt-3.5-turbo

    details about additional features or inclusions in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ndra
    -0.78
     }}
    -0.76
    town
    -0.71
    =]
    -0.68
     Rebell
    -0.68
    ocese
    -0.66
    ukong
    -0.65
    conom
    -0.64
    agog
    -0.63
     )]
    -0.63
    POSITIVE LOGITS
     DRAG
    0.73
     artwork
    0.66
     Flo
    0.66
     commentary
    0.65
     subtitles
    0.64
     featuring
    0.63
     optionally
    0.62
     emphasis
    0.62
     narration
    0.61
     nods
    0.60
    Act Density 0.762%

    No Known Activations