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

    Neuronpedia

    INDEX
    Explanations

    elements related to configuration settings in a technical document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     im
    -0.16
    im
    -0.15
    arian
    -0.15
    .advance
    -0.15
    ral
    -0.15
    Ñĩин
    -0.14
    asing
    -0.14
    à¸ĵ
    -0.14
    anna
    -0.14
     Musk
    -0.14
    POSITIVE LOGITS
    ÐĽÐ¬
    0.14
     XPAR
    0.14
    inded
    0.14
    ingt
    0.14
    CEE
    0.13
    ekl
    0.13
    hud
    0.13
    _SAFE
    0.13
    ledo
    0.13
    erosis
    0.13
    Act Density 0.005%

    No Known Activations