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

    Neuronpedia

    INDEX
    Explanations

    copyright-related terms and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (
    -0.16
    astr
    -0.15
    wards
    -0.15
     gender
    -0.14
    kinson
    -0.14
    ace
    -0.14
    bral
    -0.14
    sworth
    -0.14
    vt
    -0.14
    vens
    -0.14
    POSITIVE LOGITS
     Contributors
    0.24
    -present
    0.18
     Trustees
    0.17
     contributors
    0.17
     Regents
    0.17
     AUTHORS
    0.16
    .boost
    0.15
    ecast
    0.15
     Seznam
    0.15
    .datas
    0.15
    Act Density 0.010%

    No Known Activations