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

    Neuronpedia

    INDEX
    Explanations

    references to significant changes or impacts, particularly in economic or environmental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    their
    -0.17
     themselves
    -0.16
     their
    -0.16
    709
    -0.15
    719
    -0.15
    Their
    -0.15
    881
    -0.15
     иÑħ
    -0.15
    -bootstrap
    -0.14
     liv
    -0.14
    POSITIVE LOGITS
    iner
    0.19
    235
    0.17
    mite
    0.15
    oom
    0.14
    urr
    0.14
    ستÙħ
    0.14
    AFX
    0.14
    SEX
    0.14
    idis
    0.14
    bulk
    0.14
    Act Density 1.155%

    No Known Activations