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

    Neuronpedia

    INDEX
    Explanations

    the indefinite article "a" in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     is
    -0.52
    ش
    -0.51
    пру
    -0.48
     I
    -0.47
    Vaya
    -0.45
     
    -0.44
     gave
    -0.43
     It
    -0.42
    тя
    -0.40
     fine
    -0.40
    POSITIVE LOGITS
     houſe
    1.13
    Portale
    1.09
     Majefty
    1.08
     Efq
    0.98
     Monfieur
    0.98
     ſch
    0.97
     greateſt
    0.96
    ſelf
    0.96
     ſta
    0.94
     purpoſe
    0.94
    Act Density 0.023%

    No Known Activations