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

    Neuronpedia

    INDEX
    Explanations

    references to geographical locations or settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    swire
    -0.15
    mov
    -0.15
    ieg
    -0.15
    Ñĥла
    -0.15
    ãĥ¼ãĥĨãĤ£
    -0.15
    629
    -0.15
    ιÏİ
    -0.14
    infinity
    -0.14
    utas
    -0.14
     Valentine
    -0.14
    POSITIVE LOGITS
     occasion
    0.18
     basis
    0.17
     behalf
    0.17
    basis
    0.15
     occasions
    0.15
    usto
    0.15
    ãģ«ãģ¤
    0.14
    -site
    0.14
    875
    0.14
    odal
    0.14
    Act Density 0.263%

    No Known Activations