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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the letter 'w' in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Loch
    -0.16
    ichni
    -0.15
    esz
    -0.15
    icycle
    -0.14
     Penny
    -0.14
    stract
    -0.14
    enheim
    -0.14
    Å¡ku
    -0.14
    launcher
    -0.14
    ymce
    -0.13
    POSITIVE LOGITS
    ickets
    0.40
    onders
    0.25
    ounds
    0.25
    agers
    0.23
    ret
    0.22
    arrants
    0.22
    re
    0.22
    atches
    0.21
    ives
    0.21
    ombs
    0.21
    Act Density 0.019%

    No Known Activations