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

    Neuronpedia

    INDEX
    Explanations

    topics related to law, sanctions, and political action

    oai_token-act-pair · gemini-2.0-flash

    terms related to quitting or boycotting

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

    quitting/canceling

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Réponses
    -0.59
    ölkerung
    -0.48
     برانيه
    -0.47
    蚪
    -0.46
     embarazada
    -0.44
    estacks
    -0.44
    asana
    -0.43
     ویکی‌پدیای
    -0.42
    Lähteet
    -0.42
     réguli
    -0.42
    POSITIVE LOGITS
     quitting
    0.78
     Quit
    0.73
    boy
    0.72
     boycot
    0.72
     cancelling
    0.72
    quit
    0.71
     quit
    0.70
     canceling
    0.69
     cancels
    0.69
     boy
    0.66
    Act Density 4.137%

    No Known Activations