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

    Neuronpedia

    INDEX
    Explanations

    structured language with specific formatting markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    оза
    -0.17
    aic
    -0.15
    گاÙĩ
    -0.15
    Äįel
    -0.15
    /backend
    -0.14
    beiter
    -0.14
    ix
    -0.14
    GAN
    -0.14
    ìĽĶ
    -0.14
     Fav
    -0.14
    POSITIVE LOGITS
    arry
    0.15
     Warn
    0.15
    Warn
    0.15
    inski
    0.15
    eyJ
    0.14
    ầm
    0.14
    mallow
    0.14
    ród
    0.14
    (clock
    0.14
    ince
    0.14
    Act Density 0.001%

    No Known Activations