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

    Neuronpedia

    INDEX
    Explanations

    phrases related to warnings or dire consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    947
    -0.18
    pii
    -0.15
    TX
    -0.14
    éļĨ
    -0.14
    876
    -0.14
    Ī
    -0.14
    --------------------------------------------------------------------------↵
    -0.14
    acente
    -0.14
    ngrx
    -0.14
    EMPL
    -0.14
    POSITIVE LOGITS
     Nep
    0.26
     Ether
    0.26
     Alma
    0.25
     Hel
    0.23
    Ether
    0.23
     Omni
    0.23
     Plates
    0.22
     Jared
    0.22
     Cum
    0.22
     Book
    0.21
    Act Density 0.002%

    No Known Activations