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

    Neuronpedia

    INDEX
    Explanations

    organizations' names or abbreviations

    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
     gorilla
    -0.79
     Incredible
    -0.67
     Hiroshima
    -0.66
     Unloaded
    -0.62
    enegger
    -0.61
    ãĤª
    -0.59
    \":
    -0.59
    ãĤ°
    -0.58
    )=(
    -0.58
    --------------------------------------------------------
    -0.58
    POSITIVE LOGITS
    RC
    1.16
    FG
    1.14
    Ns
    1.12
    SA
    1.11
    Bs
    1.11
    Gs
    1.11
    VC
    1.10
    Ws
    1.10
    RM
    1.09
    FU
    1.09
    Act Density 0.193%

    No Known Activations