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

    Neuronpedia

    INDEX
    Explanations

    references to geographical locations and hierarchical levels of places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unbiased
    -0.15
    ismic
    -0.15
    sse
    -0.14
    ucer
    -0.14
    frey
    -0.14
     pán
    -0.14
    aho
    -0.14
     нам
    -0.14
    laws
    -0.13
    ron
    -0.13
    POSITIVE LOGITS
    most
    0.43
    MOST
    0.28
    /l
    0.23
    -most
    0.22
    -middle
    0.22
    -level
    0.22
    cased
    0.22
    class
    0.21
     crust
    0.20
     ech
    0.20
    Act Density 0.022%

    No Known Activations