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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating totality or completeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vara
    -0.14
     ман
    -0.14
     Oro
    -0.14
    essor
    -0.14
    ando
    -0.13
    enet
    -0.13
    _REQUIRE
    -0.13
    ORE
    -0.13
    gain
    -0.13
    skyt
    -0.13
    POSITIVE LOGITS
    LY
    0.16
    atial
    0.16
    unas
    0.15
    лÑİÑĩ
    0.15
    isz
    0.15
    zcze
    0.14
    udson
    0.14
    iyon
    0.14
    _argv
    0.14
     Uph
    0.14
    Act Density 0.018%

    No Known Activations