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

    Neuronpedia

    INDEX
    Explanations

    words related to place names or geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igue
    -0.16
    uggage
    -0.15
    wdx
    -0.14
    óz
    -0.14
     ÐļÑĢа
    -0.14
     relat
    -0.14
    ylon
    -0.14
    urname
    -0.14
    .cz
    -0.14
     relation
    -0.13
    POSITIVE LOGITS
    mor
    0.17
    gh
    0.17
    kar
    0.16
    ög
    0.16
    tiler
    0.16
    aru
    0.15
    loser
    0.15
    icher
    0.15
    rosse
    0.15
    Âłtom
    0.15
    Act Density 0.008%

    No Known Activations