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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating relationships or associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Herodotus
    -0.61
     cune
    -0.60
    MigrationBuilder
    -0.58
     Sodom
    -0.57
     Koran
    -0.57
     hierogly
    -0.57
     Osprey
    -0.54
     panoramique
    -0.54
     Boko
    -0.54
     Mahabhar
    -0.53
    POSITIVE LOGITS
    aarrggbb
    0.65
     some
    0.64
    numel
    0.61
    GEBURTSDATUM
    0.57
     ועל
    0.56
     själva
    0.56
    daß
    0.56
    Statistiche
    0.55
     the
    0.55
     many
    0.54
    Act Density 0.270%

    No Known Activations