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

    Neuronpedia

    INDEX
    Explanations

    names and terms related to geographical locations or landmarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rei
    -0.16
    iew
    -0.16
    elts
    -0.15
    160
    -0.15
    IEW
    -0.14
    ét
    -0.14
     [
    -0.14
    endale
    -0.14
     Ras
    -0.14
    ilst
    -0.14
    POSITIVE LOGITS
    ional
    0.23
    oleon
    0.20
    amura
    0.17
    ionales
    0.17
    igator
    0.17
    frage
    0.16
    ural
    0.16
    ednou
    0.15
    jav
    0.15
    uzzi
    0.15
    Act Density 0.019%

    No Known Activations