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

    Neuronpedia

    INDEX
    Explanations

    locations and specific geographic entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     opposite
    -0.38
     bună
    -0.36
     latar
    -0.35
    queles
    -0.35
     AssemblyCulture
    -0.35
    opposite
    -0.33
     Andalucía
    -0.33
     tangerang
    -0.31
     encantado
    -0.31
     aquellas
    -0.31
    POSITIVE LOGITS
    DockStyle
    0.77
     natives
    0.71
     NAACP
    0.70
    natives
    0.66
     native
    0.65
     Chamber
    0.65
    Aholisi
    0.63
     Police
    0.63
    Chamber
    0.62
    PerformLayout
    0.62
    Act Density 0.364%

    No Known Activations