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

    Neuronpedia

    INDEX
    Explanations

    statements related to actions performed by individuals or groups

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    assi
    -0.78
    orum
    -0.60
     risen
    -0.57
     Breaker
    -0.57
    usha
    -0.56
     Shining
    -0.55
    ses
    -0.55
     Flavoring
    -0.54
     usefulness
    -0.54
     runway
    -0.54
    POSITIVE LOGITS
     concurrently
    1.14
     electronically
    1.06
     privately
    1.05
     indoors
    1.01
     anonymously
    1.00
     collabor
    0.98
     differently
    0.96
     exclusively
    0.95
     cheaply
    0.94
     outdoors
    0.93
    Act Density 0.344%

    No Known Activations