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

    Neuronpedia

    INDEX
    Explanations

    references to temporal sequences and transitions in events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Himself
    -0.61
     său
    -0.61
     Houſe
    -0.60
     Cæsar
    -0.59
    ſelves
    -0.59
     herself
    -0.58
    them
    -0.57
     henne
    -0.57
     sendiri
    -0.56
     Meiji
    -0.56
    POSITIVE LOGITS
     they
    1.89
     we
    1.45
     he
    1.39
     the
    1.36
     it
    1.20
     you
    1.14
     she
    1.13
     a
    1.00
     there
    0.91
     some
    0.88
    Act Density 0.196%

    No Known Activations