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

    Neuronpedia

    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations, entities, or organizational terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angel
    -1.05
    aster
    -0.96
    prus
    -0.93
    sung
    -0.92
    aminer
    -0.91
    ancial
    -0.89
    union
    -0.87
    ration
    -0.87
    gel
    -0.87
    ache
    -0.87
    POSITIVE LOGITS
     N
    1.16
     M
    1.14
     C
    1.12
     FN
    1.05
     L
    1.05
     NF
    1.04
     E
    1.03
     R
    1.02
     A
    1.02
     Q
    1.02
    Act Density 0.357%

    No Known Activations