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

    Neuronpedia

    INDEX
    Explanations

    places where people are from

    oai_token-act-pair · gpt-3.5-turbo

    references to countries or places of origin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.70
    sbm
    -0.64
     ratings
    -0.63
    æĪ¦
    -0.62
    INAL
    -0.61
    THER
    -0.61
     evolution
    -0.61
     justification
    -0.59
    Rating
    -0.58
    Administ
    -0.58
    POSITIVE LOGITS
    ratch
    0.78
     Indies
    0.76
     shores
    0.72
     onwards
    0.72
     standpoint
    0.71
    avia
    0.70
    anish
    0.69
    orea
    0.69
    oard
    0.68
    ADA
    0.65
    Act Density 0.198%

    No Known Activations