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

    Neuronpedia

    INDEX
    Explanations

    references to different titles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hire
    -0.16
    arım
    -0.16
    EO
    -0.15
    prit
    -0.15
    batis
    -0.15
    arer
    -0.14
    ensen
    -0.14
    424
    -0.14
    atitis
    -0.14
    ese
    -0.14
    POSITIVE LOGITS
    erville
    0.16
    ì²Ļ
    0.15
    WithData
    0.15
    (éĩij
    0.14
    ooke
    0.14
    ushman
    0.14
    овÑĭй
    0.14
     Král
    0.14
     Peaks
    0.14
    ments
    0.14
    Act Density 0.005%

    No Known Activations