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

    Neuronpedia

    INDEX
    Explanations

    phrases related to instructions and operational procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ç«
    -0.16
    anka
    -0.15
    uluk
    -0.15
    rawer
    -0.15
     DUP
    -0.14
    anche
    -0.14
    shaw
    -0.14
    deck
    -0.14
    ench
    -0.14
    íģ¼
    -0.14
    POSITIVE LOGITS
    omers
    0.15
    ila
    0.14
    iera
    0.14
     clam
    0.14
    .ends
    0.13
     wrench
    0.13
    ofi
    0.13
    tplib
    0.13
    _mini
    0.13
     depress
    0.13
    Act Density 0.018%

    No Known Activations