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

    Neuronpedia

    INDEX
    Explanations

    concepts related to rationality and logical reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.76
     anonymity
    -0.64
    borgen
    -0.61
    sunter
    -0.58
     kasarigan
    -0.57
    jspb
    -0.56
    Pautan
    -0.56
    eckt
    -0.55
     Complaints
    -0.55
     Millard
    -0.54
    POSITIVE LOGITS
     racional
    1.06
     rational
    0.99
     Vernunft
    0.92
     reasoning
    0.92
     rationality
    0.89
     rationally
    0.86
     logical
    0.81
     Rational
    0.81
     sagesse
    0.80
     logic
    0.80
    Act Density 0.299%

    No Known Activations