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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to different technologies and systems

    oai_token-act-pair · gpt-3.5-turbo

    parentheses and their contents, likely related to technical specifications or terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nonpartisan
    -0.67
     hawk
    -0.67
     marsh
    -0.66
     unnamed
    -0.65
     resur
    -0.64
     sav
    -0.63
     faculties
    -0.63
     unre
    -0.63
     impe
    -0.62
     regards
    -0.61
    POSITIVE LOGITS
    SAM
    1.21
    also
    1.21
    UGC
    1.18
    aka
    1.17
    BAT
    1.17
    sometimes
    1.17
    BIP
    1.16
    FT
    1.16
    SG
    1.15
    RPG
    1.14
    Act Density 0.075%

    No Known Activations