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

    Neuronpedia

    INDEX
    Explanations

    words related to medical conditions and treatments

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to absurdity or ridiculousness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     levers
    -0.82
     allies
    -0.68
     coordin
    -0.67
     volunteers
    -0.67
     moderators
    -0.67
     contractors
    -0.66
     trustees
    -0.66
     pumps
    -0.64
     scanners
    -0.64
     narrowed
    -0.64
    POSITIVE LOGITS
    ieval
    1.08
    reality
    0.99
    oreal
    0.97
    ocalyptic
    0.96
    history
    0.96
    astical
    0.95
    livion
    0.95
    ocide
    0.94
    antasy
    0.91
    ensical
    0.90
    Act Density 0.434%

    No Known Activations