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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating central concepts or important themes in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uada
    -0.15
    ogan
    -0.15
    ugu
    -0.15
    anus
    -0.14
    bjerg
    -0.14
    åĿĬ
    -0.14
    ARGIN
    -0.14
    orks
    -0.14
    chal
    -0.14
    ubi
    -0.14
    POSITIVE LOGITS
    alion
    0.16
    asaki
    0.15
    alent
    0.15
    ETERS
    0.14
    Ľi
    0.14
    ako
    0.14
    plug
    0.14
    izik
    0.14
    -cent
    0.13
    ledger
    0.13
    Act Density 0.041%

    No Known Activations