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

    Neuronpedia

    INDEX
    Explanations

    terms related to data analysis and programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ma
    -0.26
    me
    -0.23
    li
    -0.22
    pa
    -0.21
    ses
    -0.21
    la
    -0.20
    ness
    -0.20
    med
    -0.20
    ries
    -0.19
    sWith
    -0.19
    POSITIVE LOGITS
    akov
    0.19
    yaw
    0.18
    yar
    0.18
    yas
    0.18
    ÅĽmy
    0.18
    ê¹
    0.17
    yum
    0.17
    yat
    0.17
    ño
    0.16
    Leaks
    0.16
    Act Density 0.679%

    No Known Activations