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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal frameworks and legislation

    oai_token-act-pair · gpt-3.5-turbo

    references to social justice and health equity issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Correction
    -0.66
    Ö¼
    -0.60
    dead
    -0.59
     hindsight
    -0.59
    _-
    -0.57
     Oops
    -0.56
    nery
    -0.55
    icide
    -0.55
    jri
    -0.55
    Orange
    -0.54
    POSITIVE LOGITS
     respectively
    1.28
     alike
    0.86
     intertwined
    0.83
     interconnected
    0.82
     conver
    0.80
     together
    0.78
    together
    0.73
     respective
    0.73
     converge
    0.72
    annabin
    0.68
    Act Density 0.729%

    No Known Activations