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

    Neuronpedia

    INDEX
    Explanations

    terms related to judicial processes and legal standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     and
    -0.58
     or
    -0.54
     in
    -0.54
     dis
    -0.52
    %");
    -0.52
    %%\
    -0.52
     =
    -0.51
    rinfo
    -0.51
    EndInit
    -0.50
     ${
    -0.49
    POSITIVE LOGITS
    ↵↵↵
    2.23
    ↵↵↵↵↵
    1.98
    ↵↵↵↵↵↵
    1.90
    ↵↵↵↵↵↵↵
    1.89
    ↵↵↵↵
    1.83
    ↵↵↵↵↵↵↵↵
    1.81
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.78
    ↵↵↵↵↵↵↵↵↵↵↵
    1.78
    ↵↵↵↵↵↵↵↵↵
    1.76
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.72
    Act Density 0.058%

    No Known Activations