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

    Neuronpedia

    INDEX
    Explanations

    percentages and related statistical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lang
    -0.70
    ;"></
    -0.69
    na
    -0.69
    </i>
    -0.69
     Fla
    -0.68
    LAM
    -0.68
    ations
    -0.67
    aways
    -0.67
    kling
    -0.66
     fla
    -0.65
    POSITIVE LOGITS
     \%$
    1.55
    %
    1.40
    \%
    1.25
     \%}$
    1.22
     \%
    1.19
    %+
    1.16
     percent
    1.15
     %
    1.11
    /%
    1.10
    percent
    1.09
    Act Density 0.175%

    No Known Activations