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

    Neuronpedia

    INDEX
    Explanations

    references to bonus-related content

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    makedirs
    -0.59
     skak
    -0.57
    γέν
    -0.56
    orghe
    -0.55
    änn
    -0.55
    fcntl
    -0.54
    endmodule
    -0.54
     TestBed
    -0.53
    обходи
    -0.53
    ValueStyle
    -0.53
    POSITIVE LOGITS
     bonuses
    1.36
    Bonuses
    1.36
     bonus
    1.31
     Bonus
    1.28
    bonus
    1.27
     Bonuses
    1.27
     BONUS
    1.27
    Bonus
    1.15
    BONUS
    1.04
    ônus
    0.98
    Act Density 0.003%

    No Known Activations