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

    Neuronpedia

    INDEX
    Explanations

    references to social surveys and public data

    oai_token-act-pair · gpt-3.5-turbo

    mentions of surveys and public opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     poles
    -0.63
     cones
    -0.63
     generations
    -0.62
     havens
    -0.60
     nan
    -0.60
     Palest
    -0.59
    ilded
    -0.58
     Flo
    -0.57
     Aether
    -0.57
     lasers
    -0.57
    POSITIVE LOGITS
    iple
    0.70
    gage
    0.70
    oyer
    0.65
    sectional
    0.62
    lishes
    0.62
    usional
    0.62
    ensical
    0.62
    #$
    0.61
    purpose
    0.61
    GHz
    0.61
    Act Density 0.094%

    No Known Activations