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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by a noun or a phrase that is likely to be a title or subtitle

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    azines
    -0.69
    adelphia
    -0.68
    auga
    -0.66
    pps
    -0.65
     Thousand
    -0.65
    wives
    -0.65
     Solitaire
    -0.64
    Enlarge
    -0.63
    \<
    -0.63
     Guides
    -0.63
    POSITIVE LOGITS
     contention
    1.03
     weakness
    0.94
     desperation
    0.93
     persuasion
    0.91
     differentiation
    0.84
     pride
    0.84
     excellence
    0.84
     oppression
    0.84
     accomplishment
    0.83
     shame
    0.83
    Act Density 1.003%

    No Known Activations