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

    Neuronpedia

    INDEX
    Explanations

    titles of films and literary works, particularly those with notable phrases or significant characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sf
    -0.15
     d
    -0.14
     Verg
    -0.13
     fuse
    -0.13
     mechan
    -0.13
    æŃ©
    -0.13
     propag
    -0.13
    ç«ł
    -0.12
     Beit
    -0.12
    alan
    -0.12
    POSITIVE LOGITS
    ecut
    0.15
    .localized
    0.15
    é¤
    0.14
    kuk
    0.14
    .compose
    0.14
    ReuseIdentifier
    0.14
    ucci
    0.14
    _lineno
    0.14
     Sesso
    0.14
    allis
    0.13
    Act Density 0.118%

    No Known Activations