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

    Neuronpedia

    INDEX
    Explanations

    phrases describing negative or unjust treatment

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "beat"

    np_token-act-pair-logits · gpt-4o-mini

    beat

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    клопе
    -0.71
    libft
    -0.56
    MigrationBuilder
    -0.54
    InputTagHelper
    -0.52
     (−
    -0.52
     بيها
    -0.51
    CloseOperation
    -0.50
    hdashline
    -0.50
    protoimpl
    -0.49
    slidesToShow
    -0.49
    POSITIVE LOGITS
     beat
    1.67
     beating
    1.59
     beaten
    1.36
    beat
    1.30
     BEAT
    1.28
     Beat
    1.25
     beats
    1.23
    Beat
    1.19
    BEAT
    1.15
    beaten
    1.05
    Act Density 2.120%

    No Known Activations