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

    Neuronpedia

    INDEX
    Explanations

    uncertainty or suggestion phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    حياته
    -0.61
    complexContent
    -0.60
    himself
    -0.57
    herself
    -0.57
     Himself
    -0.54
     thiệu
    -0.51
     herself
    -0.50
     AssemblyTitle
    -0.49
    bucks
    -0.48
     ete
    -0.48
    POSITIVE LOGITS
     they
    1.56
     we
    1.43
     it
    1.30
     there
    1.17
     you
    1.03
     the
    0.88
     this
    0.86
     они
    0.86
     these
    0.86
     he
    0.84
    Act Density 0.535%

    No Known Activations