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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "way" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enthal
    -0.17
    quia
    -0.15
    sten
    -0.15
    imid
    -0.15
    ews
    -0.15
    imits
    -0.15
    ν
    -0.14
    ranÃŃ
    -0.14
    ENTE
    -0.14
     ServiceException
    -0.14
    POSITIVE LOGITS
    ward
    0.22
    finding
    0.19
    ÚĺÙĩ
    0.18
    rown
    0.17
    yyy
    0.17
    yyyy
    0.17
    oshi
    0.17
    ÅĽci
    0.16
    elp
    0.16
    YYYY
    0.15
    Act Density 0.059%

    No Known Activations