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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and variables used in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    findpost
    -0.71
    tvguidetime
    -0.62
    DebuggerNonUser
    -0.59
     Außer
    -0.58
    mybatisplus
    -0.57
    География
    -0.54
    ANTLR
    -0.51
    uyasha
    -0.51
    vaux
    -0.51
     ANGELES
    -0.50
    POSITIVE LOGITS
     square
    1.17
     squared
    1.09
     squares
    1.07
     SQUARE
    1.05
    square
    1.00
     Square
    0.96
    Square
    0.93
     Squares
    0.92
    SQUARE
    0.90
    squared
    0.86
    Act Density 1.734%

    No Known Activations