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

    Neuronpedia

    INDEX
    Explanations

    terms related to assignments and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AIM
    -0.16
    resi
    -0.15
    ãĥ¬ãĤ¹
    -0.15
    ei
    -0.14
    ubits
    -0.14
    usal
    -0.14
     prec
    -0.14
    flies
    -0.14
    ksi
    -0.14
    ycz
    -0.14
    POSITIVE LOGITS
    ments
    0.25
    ment
    0.19
    ee
    0.17
    (=)
    0.16
    ñana
    0.16
    iment
    0.16
    견
    0.16
    yro
    0.15
    olean
    0.15
    ádu
    0.15
    Act Density 0.014%

    No Known Activations