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

    Neuronpedia

    INDEX
    Explanations

    terms related to risks and dangers, particularly in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uchar
    -0.17
    aqu
    -0.16
    éĢł
    -0.15
    onym
    -0.15
     Jah
    -0.14
    ury
    -0.14
    ega
    -0.14
     yerine
    -0.14
    arent
    -0.14
    ixa
    -0.14
    POSITIVE LOGITS
    lessly
    0.18
    iest
    0.16
    fully
    0.15
    DAC
    0.15
    mong
    0.14
    íħĶ
    0.14
    gaard
    0.14
    295
    0.14
     Nuggets
    0.13
    590
    0.13
    Act Density 0.053%

    No Known Activations