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

    Neuronpedia

    INDEX
    Explanations

    references to quality or excellence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adox
    -0.16
    udeau
    -0.14
    rey
    -0.14
    ãģ¬
    -0.14
    опиÑģ
    -0.14
    ATAB
    -0.14
    pee
    -0.14
    åĵ²
    -0.13
    496
    -0.13
    usta
    -0.13
    POSITIVE LOGITS
    -quality
    0.18
    stein
    0.18
    inton
    0.17
    ridge
    0.16
    ||||
    0.16
    ibraries
    0.16
    815
    0.15
    brtc
    0.15
    óng
    0.15
    ÑĤÑı
    0.14
    Act Density 0.011%

    No Known Activations