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

    Neuronpedia

    INDEX
    Explanations

    specific geographical names or identifiers related to locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Buccane
    -0.18
    äch
    -0.17
    ê
    -0.15
    ewan
    -0.15
    shed
    -0.14
    pez
    -0.14
    veal
    -0.14
     Guidance
    -0.14
    ueur
    -0.14
    üss
    -0.14
    POSITIVE LOGITS
    .lt
    0.35
     Lith
    0.34
     Lithuania
    0.34
     Vil
    0.30
    Ä
    0.29
    Å«
    0.23
     Už
    0.23
     Alg
    0.22
     Pane
    0.22
     Jonas
    0.22
    Act Density 0.014%

    No Known Activations