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

    Neuronpedia

    INDEX
    Explanations

    the use of "left" and related directional terms in mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.70
    Zitat
    -0.68
     Italijani
    -0.67
     يتيمه
    -0.67
    SharedDtor
    -0.66
    ways
    -0.63
     Cruces
    -0.61
     transfieras
    -0.60
     censi
    -0.59
    ::*;
    -0.58
    POSITIVE LOGITS
    left
    1.59
    (
    0.92
    mrow
    0.91
    <i>
    0.89
    <em>
    0.83
    __(/*!
    0.83
     left
    0.81
     giapp
    0.80
     محفوظة
    0.78
    /**
    0.77
    Act Density 0.095%

    No Known Activations