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

    Neuronpedia

    INDEX
    Explanations

    formations related to negative numerical values or errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    '},
    -0.97
    []):
    -0.89
    '],
    -0.88
    "):
    -0.88
    "])
    -0.84
    %");
    -0.84
    }");
    -0.84
    '])->
    -0.83
    "],
    -0.83
    ]");
    -0.83
    POSITIVE LOGITS
    ,-
    1.87
    ,+
    1.56
    ,--
    1.49
    ,,,
    1.46
    ,=
    1.39
    ,:
    1.38
    ,(
    1.37
    ,/
    1.36
    ,-.
    1.35
    ,_
    1.34
    Act Density 0.269%

    No Known Activations