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

    Neuronpedia

    INDEX
    Explanations

    distinctions and variations across different models or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kombin
    -0.15
    ế
    -0.15
    uth
    -0.14
    Ïįν
    -0.14
    jabi
    -0.14
    znám
    -0.14
     WithEvents
    -0.14
    anzi
    -0.13
    thern
    -0.13
    oran
    -0.13
    POSITIVE LOGITS
     across
    0.42
     Across
    0.39
     different
    0.37
    Across
    0.37
     between
    0.35
     ÑĢазнÑĭÑħ
    0.33
    ä¸įåIJĮ
    0.33
    between
    0.31
    different
    0.31
    _different
    0.31
    Act Density 0.242%

    No Known Activations