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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to various locations and people

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their actions or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Unle
    -0.68
    scription
    -0.67
    raft
    -0.65
     Speedway
    -0.64
     1954
    -0.64
     1904
    -0.64
    yss
    -0.62
    ongh
    -0.62
     Fargo
    -0.61
     Prompt
    -0.61
    POSITIVE LOGITS
     resided
    0.87
    'd
    0.78
     penetrated
    0.77
     boarded
    0.75
     reside
    0.74
     invaded
    0.73
     interacted
    0.73
     lived
    0.72
     resides
    0.72
     poked
    0.71
    Act Density 0.163%

    No Known Activations