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

    Neuronpedia

    INDEX
    Explanations

    references to third-party services and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /alert
    -0.15
    zure
    -0.15
    otti
    -0.15
    koli
    -0.14
    kat
    -0.14
    ondo
    -0.14
    оби
    -0.14
    bilt
    -0.14
    коÑĤ
    -0.14
    obby
    -0.14
    POSITIVE LOGITS
     third
    0.18
     outside
    0.18
    vise
    0.17
    第ä¸ī
    0.16
    idget
    0.16
    third
    0.15
     Wise
    0.15
    lander
    0.15
     第ä¸ī
    0.15
    outside
    0.15
    Act Density 0.016%

    No Known Activations