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

    Neuronpedia

    INDEX
    Explanations

    references to specific geographical locations, particularly islands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NX
    -0.16
     camp
    -0.15
     mesh
    -0.14
    dyn
    -0.14
     River
    -0.14
    È
    -0.14
     dyn
    -0.14
     john
    -0.14
    557
    -0.14
    -session
    -0.14
    POSITIVE LOGITS
     Canary
    0.30
     Las
    0.24
     Fu
    0.24
     Gran
    0.22
    tener
    0.21
     island
    0.21
    Fu
    0.21
    Las
    0.21
     Ade
    0.20
     Atlantic
    0.20
    Act Density 0.012%

    No Known Activations