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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and their associations within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ase
    -0.15
    LEV
    -0.14
    bos
    -0.14
    alie
    -0.14
    UGHT
    -0.14
    IDGE
    -0.14
    861
    -0.13
    аж
    -0.13
    verity
    -0.13
     moderation
    -0.13
    POSITIVE LOGITS
    addtogroup
    0.18
    yte
    0.17
    arak
    0.16
    ürk
    0.15
    mue
    0.15
     ragaz
    0.15
    thouse
    0.15
    ÑĢалÑĮ
    0.14
    rowning
    0.14
    OLT
    0.14
    Act Density 0.768%

    No Known Activations