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

    Neuronpedia

    INDEX
    Explanations

    phrases or instances of "of" indicating possession or part-whole relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cæsar
    -0.86
     Shakspeare
    -0.74
     Chriftian
    -0.63
     Jefus
    -0.63
     Mahomet
    -0.62
     Shaksp
    -0.62
     Mahabhar
    -0.62
     Oedipus
    -0.60
     Assyrian
    -0.60
     Charlemagne
    -0.59
    POSITIVE LOGITS
     the
    1.45
     an
    1.11
     a
    1.09
     their
    1.03
     our
    0.96
     its
    0.96
     this
    0.95
     what
    0.94
     sorts
    0.93
     course
    0.92
    Act Density 1.488%

    No Known Activations