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

    Neuronpedia

    INDEX
    Explanations

    references to ownership or possession

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     itſelf
    -1.16
     myſelf
    -1.06
     Efq
    -1.03
    LookAnd
    -1.02
     himſelf
    -1.00
    expandindo
    -0.98
     TestBed
    -0.98
     themſelves
    -0.98
     ſtate
    -0.94
     Monfieur
    -0.94
    POSITIVE LOGITS
     is
    0.72
     là
    0.51
    目的是
    0.51
     question
    0.48
     so
    0.47
     by
    0.45
     due
    0.44
     focus
    0.44
     let
    0.44
     $
    0.42
    Act Density 0.098%

    No Known Activations