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

    Neuronpedia

    INDEX
    Explanations

    key programming concepts and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åı£
    -0.15
    claimer
    -0.14
    ÙĦع
    -0.14
    orman
    -0.14
    deaux
    -0.14
    pong
    -0.14
    883
    -0.14
    unan
    -0.14
    ardo
    -0.14
    elli
    -0.14
    POSITIVE LOGITS
    ëĿ¼ëıĦ
    0.15
    amage
    0.14
    «a
    0.14
    éIJĺ
    0.14
    urname
    0.14
    èŀ
    0.14
     entr
    0.14
    sand
    0.14
    ertz
    0.13
    PackageName
    0.13
    Act Density 0.005%

    No Known Activations