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

    Neuronpedia

    INDEX
    Explanations

    personal interactions and relationships between individuals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Cancel
    -0.77
    UPDATE
    -0.76
    Update
    -0.73
     pending
    -0.70
     confirming
    -0.67
    osponsors
    -0.67
     UPDATE
    -0.63
     reversal
    -0.62
     reversing
    -0.62
     Ending
    -0.61
    POSITIVE LOGITS
     tended
    1.54
     wore
    1.38
     liked
    1.36
     depended
    1.34
     loved
    1.33
     knew
    1.30
     grew
    1.29
     cared
    1.28
     hated
    1.26
     lived
    1.26
    Act Density 0.396%

    No Known Activations