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

    Neuronpedia

    INDEX
    Explanations

    references to sports achievements and conference records

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Efq
    -1.25
     Jefus
    -1.15
     myſelf
    -1.15
     houſe
    -1.13
     itſelf
    -1.13
     Monfieur
    -1.10
    تقاوى
    -1.09
     Majefty
    -1.09
     pleaſure
    -1.09
     himſelf
    -1.07
    POSITIVE LOGITS
     co
    0.56
     c
    0.55
    転
    0.55
    conf
    0.52
     Sch
    0.51
    ex
    0.50
    ighton
    0.50
     to
    0.50
    Ậ
    0.49
     Ag
    0.48
    Act Density 0.006%

    No Known Activations