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

    Neuronpedia

    INDEX
    Explanations

    tokens that indicate confidentiality or privacy-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -addon
    -0.19
    oto
    -0.16
     addCriterion
    -0.15
    elen
    -0.15
    MBOL
    -0.15
    adder
    -0.14
    etten
    -0.14
    ahat
    -0.14
    OTO
    -0.14
    thon
    -0.14
    POSITIVE LOGITS
    iero
    0.15
    ĵåIJį
    0.14
    jÃŃž
    0.14
     Tro
    0.14
    Stick
    0.14
     Stick
    0.13
    HeaderValue
    0.13
    mania
    0.13
    ãĥ¥
    0.13
     Robertson
    0.13
    Act Density 0.015%

    No Known Activations