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

    Neuronpedia

    INDEX
    Explanations

    statistical data and percentages related to demographics or research results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rics
    -0.17
    elop
    -0.17
    481
    -0.16
    burgh
    -0.16
    ervlet
    -0.15
    ONUS
    -0.15
    uve
    -0.14
    mil
    -0.14
    iez
    -0.14
     Cage
    -0.14
    POSITIVE LOGITS
    estar
    0.16
    åij¨
    0.14
    usters
    0.13
     об
    0.13
    outil
    0.13
    ола
    0.13
    avy
    0.13
     Bundes
    0.13
     Laurent
    0.13
     Stark
    0.13
    Act Density 0.026%

    No Known Activations