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

    Neuronpedia

    INDEX
    Explanations

    mentions of times, locations, and actions related to news updates and political events

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     proportions
    -0.59
     Defendants
    -0.58
    shall
    -0.58
     ancest
    -0.55
    emale
    -0.55
     digits
    -0.55
     bearer
    -0.55
     attachment
    -0.55
     withd
    -0.54
    units
    -0.54
    POSITIVE LOGITS
     GOODMAN
    0.89
     partName
    0.81
    odcast
    0.77
     WEEK
    0.76
    .--
    0.73
     Oops
    0.73
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.73
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.71
    âķIJâķIJ
    0.70
    nce
    0.69
    Act Density 6.821%

    No Known Activations