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

    Neuronpedia

    INDEX
    Explanations

    descriptions of scenic locations and tourist attractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lakes
    -0.22
     Lake
    -0.21
     lake
    -0.21
    Lake
    -0.18
     pond
    -0.18
     Lakes
    -0.17
     swamp
    -0.17
     Colonial
    -0.16
     Canal
    -0.15
     river
    -0.15
    POSITIVE LOGITS
     Lyme
    0.22
     cliffs
    0.21
     Mev
    0.21
    Portland
    0.20
     Portland
    0.20
     cliff
    0.19
     tide
    0.19
     Fist
    0.18
     Toe
    0.18
     rocks
    0.18
    Act Density 0.062%

    No Known Activations