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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating geographical locations or boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Consort
    -0.16
    ève
    -0.15
    atron
    -0.15
    ãĥ¼ãĤº
    -0.14
    ehir
    -0.14
     Knot
    -0.14
    ाव
    -0.14
    ruise
    -0.14
    odium
    -0.13
    åħ¥ãĤĬ
    -0.13
    POSITIVE LOGITS
    most
    0.19
    -most
    0.16
     serving
    0.15
     Serving
    0.15
    libs
    0.14
    uent
    0.14
    éľŀ
    0.14
    terr
    0.14
     Park
    0.13
    -circle
    0.13
    Act Density 0.035%

    No Known Activations