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

    Neuronpedia

    INDEX
    Explanations

    references to objective facts and their verification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lump
    -0.16
    die
    -0.15
     Trib
    -0.14
    .idx
    -0.14
     Leer
    -0.14
    /fw
    -0.14
    ded
    -0.13
    ļ
    -0.13
    erot
    -0.13
    fine
    -0.13
    POSITIVE LOGITS
    itious
    0.20
    facts
    0.20
     facts
    0.20
    intl
    0.17
    ually
    0.16
    Fact
    0.16
    çı
    0.15
     fact
    0.15
    ysqli
    0.15
    uguay
    0.15
    Act Density 0.027%

    No Known Activations