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

    Neuronpedia

    INDEX
    Explanations

    terms related to variations from a norm or standard

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ³ãĥĨãĤ£
    -0.17
    baum
    -0.16
    baÅŁ
    -0.15
    ì§ľ
    -0.15
    絡
    -0.14
    .getOwnProperty
    -0.14
    ovah
    -0.14
    hoff
    -0.14
    cka
    -0.14
    IRST
    -0.14
    POSITIVE LOGITS
    vg
    0.15
    اتÙĩ
    0.15
    uru
    0.15
    905
    0.15
    ici
    0.15
    iven
    0.15
    º«
    0.15
    anda
    0.14
     unspecified
    0.14
    vd
    0.14
    Act Density 0.009%

    No Known Activations