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

    Neuronpedia

    INDEX
    Explanations

    references to political affiliations and lobbying

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    statt
    -0.16
    abile
    -0.15
     haciendo
    -0.14
    ãģ¨ãģĦ
    -0.14
     arada
    -0.14
    este
    -0.14
     ederek
    -0.14
     INTERRUPTION
    -0.13
    LError
    -0.13
    ÑĢаÑĩ
    -0.13
    POSITIVE LOGITS
     who
    0.57
    who
    0.46
     qui
    0.33
     Who
    0.32
    Who
    0.30
     whom
    0.29
     quien
    0.29
     whose
    0.29
     quienes
    0.28
     kteÅĻÃŃ
    0.23
    Act Density 0.154%

    No Known Activations