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

    Neuronpedia

    INDEX
    Explanations

    references to skyscrapers and notable tall buildings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Patch
    -0.16
     patch
    -0.16
     Ign
    -0.15
     positive
    -0.14
    yon
    -0.14
     Down
    -0.14
    ign
    -0.14
     Swe
    -0.14
    utow
    -0.14
    ión
    -0.14
    POSITIVE LOGITS
    inka
    0.16
    ixel
    0.16
     shells
    0.15
    conc
    0.15
    ADDE
    0.14
    inned
    0.14
    -mails
    0.14
    é«ĺæ¸ħ
    0.14
    odb
    0.14
    czy
    0.14
    Act Density 0.048%

    No Known Activations