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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating capability, permission, and necessity within processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.94
     AssemblyCompany
    -0.87
     Мексичка
    -0.77
    Демографія
    -0.77
    afone
    -0.73
    XtraGrid
    -0.72
    IsMutable
    -0.70
    gameserver
    -0.70
     ་་
    -0.67
     debout
    -0.66
    POSITIVE LOGITS
     you
    0.73
     people
    0.69
     us
    0.68
     we
    0.65
     someone
    0.61
     agar
    0.56
     sich
    0.54
    fä
    0.54
    大家
    0.53
     everyone
    0.51
    Act Density 0.315%

    No Known Activations