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

    Neuronpedia

    INDEX
    Explanations

    references to checking out or highlighting information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .nlm
    -0.17
    URLRequest
    -0.15
    REM
    -0.14
    iddy
    -0.14
    iral
    -0.14
    ua
    -0.14
    491
    -0.14
    âĨIJ
    -0.14
     Sesso
    -0.14
    _initializer
    -0.14
    POSITIVE LOGITS
    gram
    0.17
    OTES
    0.17
    hti
    0.16
    rede
    0.16
     Ingram
    0.15
    åĢĴ
    0.15
    kre
    0.15
    Revision
    0.15
    ersiz
    0.15
    VERS
    0.14
    Act Density 0.004%

    No Known Activations