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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the concept of "one" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    تÙĥ
    -0.15
    edio
    -0.15
    mojom
    -0.14
    -NLS
    -0.14
    Routine
    -0.14
    jeme
    -0.14
    .LayoutStyle
    -0.14
    üb
    -0.14
    ibus
    -0.14
    inand
    -0.14
    POSITIVE LOGITS
     ÑģÑĢазÑĥ
    0.15
     Gar
    0.14
     gar
    0.14
    оки
    0.14
    awks
    0.14
    -half
    0.14
    ennie
    0.14
    reat
    0.13
    illac
    0.13
    Streaming
    0.13
    Act Density 0.019%

    No Known Activations