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

    Neuronpedia

    INDEX
    Explanations

    prepositions and phrases indicating relationships or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utch
    -0.15
     aw
    -0.15
    uters
    -0.14
    алÑĸ
    -0.14
    antu
    -0.14
    rawn
    -0.14
    RowIndex
    -0.13
    ingle
    -0.13
    awan
    -0.13
     around
    -0.13
    POSITIVE LOGITS
    theon
    0.16
    ugu
    0.15
     Diss
    0.15
    .ct
    0.14
    âĢ¦↵↵↵
    0.14
     Acid
    0.14
    'gc
    0.14
    ãĥ¼ãĥŃ
    0.14
    olle
    0.13
    deaux
    0.13
    Act Density 0.035%

    No Known Activations