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

    Neuronpedia

    INDEX
    Explanations

    assignment statements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    crom
    -0.84
     crom
    -0.69
     Clarke
    -0.63
    äfts
    -0.62
    -
    -0.61
    gouv
    -0.61
     Ros
    -0.60
    ниципа
    -0.57
    INC
    -0.57
     Roca
    -0.57
    POSITIVE LOGITS
     :=
    2.57
    :=
    1.70
    :=\
    1.50
    ):=\
    1.45
    }:=\
    1.44
    }:=
    1.29
    ):=
    1.23
    ✨:
    0.87
     feroit
    0.85
     Burrow
    0.83
    Act Density 0.077%

    No Known Activations