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

    Neuronpedia

    INDEX
    Explanations

    locations and entities related to politics and international relations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific locations or regions in the context of various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atorium
    -0.74
    orem
    -0.72
    xb
    -0.72
    rix
    -0.71
    itol
    -0.71
    rupted
    -0.68
    onomy
    -0.66
    pheus
    -0.65
    rm
    -0.65
    aea
    -0.65
    POSITIVE LOGITS
     respectively
    2.45
     etc
    1.29
     among
    1.23
    depending
    1.20
     alike
    1.18
     whichever
    1.18
     depending
    1.15
     plus
    1.13
    etc
    1.09
    among
    1.08
    Act Density 0.282%

    No Known Activations