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

    Neuronpedia

    INDEX
    Explanations

    acronyms related to organizations and projects

    oai_token-act-pair · gpt-3.5-turbo

    acronyms or abbreviations related to organizations or programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Geral
    -0.65
     Alban
    -0.65
     Gors
    -0.64
    strings
    -0.64
    scroll
    -0.63
     Xuan
    -0.61
    ulet
    -0.61
    stroke
    -0.60
    iary
    -0.60
    ghai
    -0.60
    POSITIVE LOGITS
    IUM
    1.32
    ITE
    1.22
    WARE
    1.19
    FORM
    1.17
    WORK
    1.13
    PASS
    1.12
    ANCE
    1.10
    EN
    1.09
    ET
    1.09
    DATA
    1.09
    Act Density 0.150%

    No Known Activations