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

    Neuronpedia

    INDEX
    Explanations

    bracket and brace characters used in programming and mathematical equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.97
    RegressionTest
    -0.86
    transQ
    -0.86
    onOptions
    -0.85
     GenerationType
    -0.82
    ValueStyle
    -0.81
     NSCoder
    -0.81
     queſta
    -0.78
     protoimpl
    -0.77
    FunctionFlags
    -0.77
    POSITIVE LOGITS
     the
    0.95
     a
    0.55
     The
    0.48
    the
    0.44
     Cane
    0.41
    The
    0.40
    :
    0.39
     local
    0.39
     THE
    0.37
     their
    0.36
    Act Density 0.087%

    No Known Activations