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

    Neuronpedia

    INDEX
    Explanations

    references to utility classes and data structures in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.46
    Membership
    -0.45
    Câu
    -0.44
     doğum
    -0.43
    føring
    -0.42
     karşı
    -0.42
    følgelig
    -0.42
    ⓧ
    -0.41
     kysy
    -0.41
     magnético
    -0.41
    POSITIVE LOGITS
    util
    2.31
     util
    1.88
     Util
    1.71
    Util
    1.65
    UTIL
    1.51
     UTIL
    1.20
     utilitarian
    1.12
     utility
    1.11
     uti
    1.02
    utili
    1.02
    Act Density 0.026%

    No Known Activations