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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparison or relationships between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orem
    -0.19
    ik
    -0.16
     exactly
    -0.15
    iland
    -0.14
    an
    -0.14
     indeed
    -0.14
    CLUDING
    -0.14
     exact
    -0.14
    chg
    -0.13
     Policies
    -0.13
    POSITIVE LOGITS
     other
    0.17
    other
    0.17
    лиÑĨ
    0.16
     Cruc
    0.16
    êu
    0.15
     ساÛĮر
    0.15
    'autres
    0.14
    tual
    0.14
     altre
    0.14
    EEK
    0.14
    Act Density 0.026%

    No Known Activations