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

    Neuronpedia

    INDEX
    Explanations

    terms related to evaluating performance and functionality in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loo
    -0.18
    (íģ¬ê¸°
    -0.16
    vak
    -0.14
     Glory
    -0.14
    anon
    -0.14
    toolbox
    -0.14
    kiem
    -0.14
    quiz
    -0.13
     Annie
    -0.13
    weis
    -0.13
    POSITIVE LOGITS
    inal
    0.16
    aceous
    0.14
    ward
    0.14
    able
    0.14
    imate
    0.13
    ovacÃŃ
    0.13
    naire
    0.13
    uckle
    0.13
     category
    0.13
    âĢIJ
    0.13
    Act Density 0.104%

    No Known Activations