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

    Neuronpedia

    INDEX
    Explanations

    numerical and statistical information related to various topics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    vertisements
    -0.77
     airs
    -0.74
     moderator
    -0.70
     workshops
    -0.68
    farious
    -0.63
     ceremonies
    -0.61
     spont
    -0.60
     documentaries
    -0.59
    Ħ¢
    -0.58
     rituals
    -0.58
    POSITIVE LOGITS
    amount
    0.93
     equivalent
    0.92
     dwar
    0.92
    enough
    0.92
     astronomical
    0.90
     averages
    0.86
     equate
    0.85
     compares
    0.85
     compared
    0.84
     astron
    0.84
    Act Density 0.299%

    No Known Activations