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

    Neuronpedia

    INDEX
    Explanations

    articles and quantifiers that specify quantities or types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Meanwhile
    -0.15
    cloth
    -0.15
    errar
    -0.14
    umat
    -0.14
    _inches
    -0.13
    astro
    -0.13
    illus
    -0.13
    ãĥ¼ãĥĭ
    -0.13
    cuda
    -0.13
    ole
    -0.13
    POSITIVE LOGITS
    maal
    0.19
    ltra
    0.17
    λά
    0.16
     altro
    0.15
    herits
    0.15
    chantment
    0.14
     particular
    0.14
    maya
    0.14
    bob
    0.14
    irse
    0.14
    Act Density 0.036%

    No Known Activations