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

    Neuronpedia

    INDEX
    Explanations

    instances of the double underscore, typically used for special methods in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PushButton
    -0.15
    inx
    -0.15
    å®Ŀ
    -0.14
    agrams
    -0.14
    rup
    -0.14
    asio
    -0.14
    trak
    -0.14
    åħ¬
    -0.14
     starring
    -0.14
    kovÄĽ
    -0.14
    POSITIVE LOGITS
    azzo
    0.16
    uster
    0.16
     transports
    0.15
    ocab
    0.14
    ê´Ģ
    0.14
     vag
    0.14
    alse
    0.14
    LEAN
    0.14
    еви
    0.14
    572
    0.14
    Act Density 0.002%

    No Known Activations