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

    Neuronpedia

    INDEX
    Explanations

    phrases related to situations or objects being 'out of' something or having specific specifications

    oai_token-act-pair · gpt-3.5-turbo

    references to being out of control or situations involving lack of governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulhu
    -0.78
     Phi
    -0.69
    Ń·
    -0.66
    anos
    -0.65
     Horus
    -0.65
     Doomsday
    -0.64
    ebus
    -0.61
    姫
    -0.61
     md
    -0.61
     Confederation
    -0.61
    POSITIVE LOGITS
    performing
    1.09
    dated
    1.08
    numbered
    1.07
    put
    0.98
    of
    0.97
    front
    0.95
    raised
    0.95
    educated
    0.95
    produced
    0.94
    spoken
    0.92
    Act Density 0.019%

    No Known Activations