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

    Neuronpedia

    INDEX
    Explanations

    acronyms and references to scientific journals or publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /rfc
    -0.15
     Maze
    -0.14
    reen
    -0.14
    ulos
    -0.14
    OND
    -0.14
     Geg
    -0.14
     Hatch
    -0.13
    artin
    -0.13
    YPE
    -0.13
     Blob
    -0.13
    POSITIVE LOGITS
    hw
    0.16
    tÃŃ
    0.15
    endor
    0.15
    ilst
    0.15
    å¯
    0.14
    祥
    0.14
    .rel
    0.14
    istration
    0.14
    /Dk
    0.14
    tics
    0.14
    Act Density 0.118%

    No Known Activations