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

    Neuronpedia

    INDEX
    Explanations

    statements related to consumer rights and fairness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    following "is" expressing negativity or disagreement

    np_acts-logits-general · gemini-2.0-flash

    unreasonable judgments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.48
     الرياضيه
    -0.43
     sekal
    -0.40
     advirtió
    -0.38
     policías
    -0.38
     dificuldade
    -0.37
     difíciles
    -0.37
     universitarios
    -0.37
     برانيه
    -0.36
     largas
    -0.36
    POSITIVE LOGITS
     ridiculous
    0.79
     illogical
    0.70
     absurd
    0.69
     ludicrous
    0.65
     unfair
    0.64
     irresponsible
    0.64
     unacceptable
    0.63
     absurdity
    0.63
     irrational
    0.61
     unreasonable
    0.61
    Act Density 0.699%

    No Known Activations