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

    Neuronpedia

    INDEX
    Explanations

    references to examples or specific instances in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.58
    Carriera
    -0.56
     båda
    -0.56
    ValueStyle
    -0.53
     ſame
    -0.51
    ̀u
    -0.51
     насељу
    -0.50
     XNUMX
    -0.49
     Majefty
    -0.49
    rrggbb
    -0.48
    POSITIVE LOGITS
     those
    1.83
    those
    1.43
     Those
    1.18
    Those
    1.11
     celles
    1.05
     THOSE
    1.04
     ones
    1.00
     quelli
    1.00
     celui
    0.97
     namely
    0.97
    Act Density 0.420%

    No Known Activations