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

    Neuronpedia

    INDEX
    Explanations

    the word "that" and its various uses in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iv
    -0.19
    outil
    -0.15
    ault
    -0.15
    lio
    -0.15
    itag
    -0.15
    ave
    -0.15
    ivil
    -0.14
    ivent
    -0.14
    cop
    -0.14
    isky
    -0.14
    POSITIVE LOGITS
     of
    0.17
    zelf
    0.16
     ones
    0.16
    ISP
    0.16
    awks
    0.15
    venge
    0.14
     của
    0.14
    erse
    0.14
    ATOM
    0.14
    oria
    0.13
    Act Density 0.031%

    No Known Activations