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

    Neuronpedia

    INDEX
    Explanations

    specific negative words and phrases

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Solitaire
    -0.90
     Tags
    -0.80
     Scrib
    -0.78
     Puzzles
    -0.75
    ulhu
    -0.74
     ROCK
    -0.73
     Tribe
    -0.71
     Borders
    -0.70
     Compass
    -0.70
     Indigo
    -0.69
    POSITIVE LOGITS
    awaited
    1.33
    needed
    1.26
    anticipated
    1.26
    earned
    1.13
    respected
    1.10
    known
    1.10
    sized
    1.09
    equipped
    1.08
    handled
    1.07
    produced
    1.07
    Act Density 0.030%

    No Known Activations