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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negation or denial of some kind

    oai_token-act-pair · gpt-3.5-turbo

    terms related to medical necessity and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortment
    -0.72
    tnc
    -0.69
    haul
    -0.67
    éĹĺ
    -0.66
    incial
    -0.63
    rahim
    -0.62
     ACTIONS
    -0.62
    href
    -0.61
    YES
    -0.61
    SAN
    -0.60
    POSITIVE LOGITS
     anymore
    1.77
     nor
    1.49
     necessarily
    1.08
     anywhere
    1.00
     whatsoever
    0.97
     slightest
    0.97
    yet
    0.92
     yet
    0.88
     anybody
    0.86
     anything
    0.86
    Act Density 0.410%

    No Known Activations