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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific locations or words related to geography

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    eering
    -0.70
    Reviewer
    -0.67
     striving
    -0.63
    RESULTS
    -0.62
    direction
    -0.61
     aven
    -0.61
    main
    -0.59
     dishon
    -0.56
     marching
    -0.56
     Passive
    -0.55
    POSITIVE LOGITS
    't
    1.23
    berra
    1.18
    vas
    1.11
    adian
    1.02
    opy
    1.02
    isters
    0.94
    ister
    0.89
    icum
    0.86
    nery
    0.86
    thus
    0.85
    Act Density 0.595%

    No Known Activations