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

    Neuronpedia

    INDEX
    Explanations

    references to official declarations or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irit
    -0.15
    .Interop
    -0.15
    Uvs
    -0.15
    Ä°ng
    -0.14
    osate
    -0.13
     обл
    -0.13
    akers
    -0.13
    аÑĢÑı
    -0.13
    kili
    -0.13
    ify
    -0.13
    POSITIVE LOGITS
    éĢģæĸĻçĦ¡æĸĻ
    0.14
    PLEX
    0.14
    imeo
    0.14
    Rol
    0.14
     Rol
    0.14
    eron
    0.14
    zl
    0.13
    åĩĢ
    0.13
    à¸ģรรม
    0.13
    æŀ¶
    0.13
    Act Density 0.016%

    No Known Activations