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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "for."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LECT
    -0.14
    aries
    -0.14
    iro
    -0.13
    ieri
    -0.13
    vier
    -0.13
    aki
    -0.13
    inine
    -0.13
    esc
    -0.13
     assorted
    -0.13
    ãģ®ãģ¿
    -0.13
    POSITIVE LOGITS
     example
    0.32
    cing
    0.24
     Example
    0.24
     instance
    0.24
     exemple
    0.24
    example
    0.24
    unately
    0.23
     ÙħثاÙĦ
    0.21
     ejemplo
    0.20
    -example
    0.20
    Act Density 0.077%

    No Known Activations