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

    Neuronpedia

    INDEX
    Explanations

    the word "fact" followed by a statement or observation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal beliefs or statements of opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bowl
    -0.70
    rolling
    -0.69
    area
    -0.66
    apo
    -0.64
    ogie
    -0.64
    LC
    -0.62
    cox
    -0.61
    ouses
    -0.61
     airs
    -0.60
    odon
    -0.60
    POSITIVE LOGITS
     quite
    0.76
     downright
    0.74
     worse
    0.70
     overest
    0.65
     reverse
    0.63
    bnb
    0.62
    sterdam
    0.60
    oln
    0.59
    ocry
    0.59
     pretty
    0.59
    Act Density 0.216%

    No Known Activations