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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate connectivity or relationships between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rych
    -0.17
    Ñħи
    -0.16
    chet
    -0.15
    coon
    -0.14
    æ¯
    -0.14
    æĺ¯æĪij
    -0.14
    кав
    -0.13
    rente
    -0.13
    chyb
    -0.13
    anas
    -0.13
    POSITIVE LOGITS
     the
    0.14
    aupt
    0.13
    _via
    0.13
     оÑģновном
    0.13
    âħ
    0.13
     what
    0.13
     Qu
    0.13
     qu
    0.12
    gether
    0.12
     it
    0.12
    Act Density 0.907%

    No Known Activations