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

    Neuronpedia

    INDEX
    Explanations

    phrases related to policy, governance, and decision-making

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    amins
    -0.63
    bill
    -0.62
    soDeliveryDate
    -0.59
    amina
    -0.55
     Trip
    -0.52
    azeera
    -0.50
     charism
    -0.49
     denominations
    -0.49
    igans
    -0.49
    nan
    -0.49
    POSITIVE LOGITS
    of
    0.70
     whereby
    0.70
    Ī
    0.65
    xxxxxxxx
    0.62
    ender
    0.59
    ãĤ£
    0.59
    urst
    0.59
    below
    0.59
    ACTED
    0.58
    behind
    0.58
    Act Density 16.930%

    No Known Activations