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

    Neuronpedia

    INDEX
    Explanations

    references to specific islands or island-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oceans
    -0.19
    mir
    -0.17
     Ocean
    -0.16
     ocean
    -0.16
    .safe
    -0.15
    enville
    -0.15
    Safe
    -0.15
    latable
    -0.15
     mir
    -0.15
     Bay
    -0.15
    POSITIVE LOGITS
     Lesb
    0.20
     ön
    0.19
     Serif
    0.18
     Ãİ
    0.18
     Hispan
    0.18
     Flores
    0.17
     Jersey
    0.17
    ierz
    0.17
    Ãİ
    0.16
    inker
    0.16
    Act Density 0.078%

    No Known Activations