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

    Neuronpedia

    INDEX
    Explanations

    locations and geographical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jacksonville
    -0.20
     Jakarta
    -0.17
     Miami
    -0.16
    Eb
    -0.16
     Louisiana
    -0.16
    Florida
    -0.16
     Trinidad
    -0.15
    igua
    -0.15
    Miami
    -0.15
    quina
    -0.15
    POSITIVE LOGITS
     glacier
    0.32
     snow
    0.32
     Glacier
    0.30
     Balt
    0.30
     Himal
    0.30
     glaciers
    0.29
     Snow
    0.28
    snow
    0.27
     Alpine
    0.27
     Ski
    0.27
    Act Density 0.034%

    No Known Activations