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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating proposals for change or reform

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.72
     متعلقه
    -0.65
    Izvori
    -0.63
    Tembelea
    -0.60
     فريبيس
    -0.54
    יצד
    -0.54
    RectangleBorder
    -0.54
    Климат
    -0.53
    marginVertical
    -0.53
     gynhyrchwyd
    -0.52
    POSITIVE LOGITS
     culture
    0.60
     ethic
    0.55
     culte
    0.54
     cultuur
    0.53
    culture
    0.52
     just
    0.52
     Tobin
    0.51
     Culture
    0.51
     väx
    0.51
     cultura
    0.51
    Act Density 0.403%

    No Known Activations