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

    Neuronpedia

    INDEX
    Explanations

    language related to human impact and interactions with the environment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uffle
    -0.20
    anner
    -0.17
    ezi
    -0.17
    imu
    -0.17
    .codes
    -0.16
    инов
    -0.16
    æģ¯
    -0.16
    tero
    -0.15
     Wikispecies
    -0.15
    theon
    -0.14
    POSITIVE LOGITS
    .scalablytyped
    0.17
    tracted
    0.16
    edith
    0.16
    ìĸij
    0.15
    uros
    0.15
     surfaces
    0.14
    akit
    0.14
    itch
    0.14
     Tar
    0.14
    _tabs
    0.13
    Act Density 0.190%

    No Known Activations