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

    Neuronpedia

    INDEX
    Explanations

    phrases related to activities and events in a community, such as meetings, markets, and public appearances

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ivation
    -0.60
    iances
    -0.53
     declass
    -0.52
    arna
    -0.51
    iance
    -0.51
    orney
    -0.49
    ivating
    -0.49
    masters
    -0.49
     Kremlin
    -0.48
    atories
    -0.48
    POSITIVE LOGITS
    earch
    0.83
    erve
    0.78
    cape
    0.75
    nes
    0.74
    forth
    0.73
    creen
    0.73
    eed
    0.73
    iac
    0.71
    ville
    0.70
    itters
    0.70
    Act Density 10.381%

    No Known Activations