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

    Neuronpedia

    INDEX
    Explanations

    mathematical operators and symbols used in programming or mathematical expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Hel
    -0.73
    ات
    -0.68
    🤣🤣
    -0.65
     Jav
    -0.65
    ARES
    -0.64
     Kao
    -0.63
    Cons
    -0.60
    Hel
    -0.59
     Pros
    -0.58
     справ
    -0.57
    POSITIVE LOGITS
    -*
    0.98
     Majefty
    0.97
     Monfieur
    0.96
    -?
    0.96
     myſelf
    0.95
     setuptools
    0.95
    -<
    0.94
     '-':
    0.92
    )-\
    0.92
    -#
    0.92
    Act Density 0.037%

    No Known Activations