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

    Neuronpedia

    INDEX
    Explanations

    references to cultural institutions and their organizational structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atra
    -0.18
    gs
    -0.15
    itan
    -0.14
    oll
    -0.14
    add
    -0.14
     dating
    -0.14
    aver
    -0.14
    unt
    -0.14
    FT
    -0.14
    Haz
    -0.14
    POSITIVE LOGITS
    MOTE
    0.16
    chwitz
    0.16
    utherford
    0.15
     Tib
    0.15
    RowAt
    0.15
     heap
    0.14
    piler
    0.14
    awah
    0.14
    odash
    0.14
    cci
    0.14
    Act Density 0.283%

    No Known Activations