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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and various phrases related to patents and legal documents

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    LElement
    -0.90
     faſt
    -0.88
     Efq
    -0.85
     zelve
    -0.82
     myſelf
    -0.82
     purpoſe
    -0.80
     tiegħek
    -0.79
    ."</
    -0.78
     poffible
    -0.77
     whoſe
    -0.76
    POSITIVE LOGITS
     
    0.64
     short
    0.55
    '
    0.53
    ,
    0.51
     “
    0.50
    :///
    0.50
     of
    0.50
     rec
    0.49
     "
    0.48
     best
    0.48
    Act Density 0.005%

    No Known Activations