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

    Neuronpedia

    INDEX
    Explanations

    references to war and conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ede
    -0.16
    PERT
    -0.15
    arest
    -0.15
    enn
    -0.15
    otts
    -0.15
    aurus
    -0.15
     неÑģ
    -0.15
    empl
    -0.14
    ë£Į
    -0.14
    ยà¸Ļà¸ķ
    -0.14
    POSITIVE LOGITS
    lord
    0.23
    lock
    0.20
    rior
    0.20
    lords
    0.20
    rier
    0.19
    fare
    0.18
    like
    0.17
    bler
    0.17
    front
    0.17
    blers
    0.17
    Act Density 0.036%

    No Known Activations