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

    Neuronpedia

    INDEX
    Explanations

    references to personal life events, actions, and relationships

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating relationships and personal affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Were
    -0.75
    URN
    -0.72
     Ended
    -0.72
    Then
    -0.68
    apter
    -0.68
    ÙIJ
    -0.67
    urations
    -0.65
    rived
    -0.64
    RAL
    -0.64
    âĶĢâĶĢâĶĢâĶĢ
    -0.63
    POSITIVE LOGITS
     insists
    1.47
     intends
    1.44
     accuses
    1.41
     refuses
    1.37
     believes
    1.34
     prefers
    1.32
     expects
    1.29
     enjoys
    1.28
     maintains
    1.28
     opposes
    1.28
    Act Density 0.744%

    No Known Activations