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

    Neuronpedia

    INDEX
    Explanations

    references to community engagement and collaborative projects aimed at improving societal conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Organization
    -0.16
     behaviors
    -0.16
    adow
    -0.15
    Armor
    -0.15
    AUTHORIZED
    -0.15
     Birmingham
    -0.14
    ãĥĸãĥª
    -0.14
     autos
    -0.14
    adr
    -0.14
    upal
    -0.14
    POSITIVE LOGITS
     lekker
    0.43
     Gaut
    0.41
     Johannesburg
    0.41
     Cape
    0.39
    .za
    0.36
     Afrika
    0.33
     isi
    0.32
     South
    0.31
     SA
    0.30
     apartheid
    0.29
    Act Density 0.535%

    No Known Activations