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

    Neuronpedia

    INDEX
    Explanations

    terms related to research publications and metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rug
    -0.18
    ------+------+
    -0.16
    ugh
    -0.15
    ayscale
    -0.14
    اÙĨÙĩ
    -0.14
    abyrin
    -0.14
     conc
    -0.13
    Ùıس
    -0.13
    -gap
    -0.13
    alink
    -0.13
    POSITIVE LOGITS
    ürn
    0.15
    ALA
    0.15
    .radians
    0.14
    äºŃ
    0.14
     Garland
    0.14
     Jasmine
    0.14
    bj
    0.14
     gravity
    0.14
    apon
    0.13
    lotte
    0.13
    Act Density 0.002%

    No Known Activations