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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing denial and the lack of responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    peated
    -0.14
    _COMPAT
    -0.14
    ltra
    -0.14
     lø
    -0.13
     Kash
    -0.13
    ition
    -0.13
    MOOTH
    -0.13
    ive
    -0.12
    ssel
    -0.12
    steder
    -0.12
    POSITIVE LOGITS
    ug
    0.15
    ipel
    0.15
    ieux
    0.14
    ilde
    0.14
    CommandEvent
    0.14
    AndGet
    0.14
    iego
    0.14
    ozem
    0.14
    umas
    0.14
    upal
    0.13
    Act Density 0.017%

    No Known Activations