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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emphasis or certainty

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     LAT
    -0.70
    umbnail
    -0.64
     Cheong
    -0.63
     Current
    -0.63
    ociate
    -0.62
    transfer
    -0.61
    éĹĺ
    -0.61
    luaj
    -0.60
    iling
    -0.60
    udi
    -0.58
    POSITIVE LOGITS
     raining
    1.12
     easier
    1.09
     impossible
    1.08
     advisable
    0.99
     easy
    0.99
     unclear
    0.99
     difficult
    0.94
     prudent
    0.92
     awhile
    0.89
     possible
    0.89
    Act Density 0.094%

    No Known Activations