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

    Neuronpedia

    INDEX
    Explanations

    technical terms and conditions related to programming and functionality checks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ackers
    -0.15
    egas
    -0.15
    Äħż
    -0.15
    رد
    -0.14
    .isEnabled
    -0.14
    xmax
    -0.14
    KEN
    -0.13
     mil
    -0.13
    utton
    -0.13
    .Raw
    -0.13
    POSITIVE LOGITS
    arium
    0.16
    abs
    0.15
    utan
    0.15
    quan
    0.14
     Stafford
    0.14
    cab
    0.14
    plex
    0.14
    lands
    0.14
    adero
    0.14
     Trustees
    0.13
    Act Density 0.194%

    No Known Activations