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

    Neuronpedia

    INDEX
    Explanations

    words related to historical figures and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.62
    uldron
    -0.57
    ERVIS
    -0.56
     member
    -0.55
    ricane
    -0.55
    Personendaten
    -0.54
     Minden
    -0.54
    Conta
    -0.53
    intr
    -0.53
     internetowa
    -0.53
    POSITIVE LOGITS
     himself
    0.88
    himself
    0.69
     Himself
    0.66
    SerializeField
    0.66
    lusconi
    0.65
     législation
    0.62
    quiao
    0.60
    manjaro
    0.58
     desnuda
    0.56
    UnitTesting
    0.56
    Act Density 0.341%

    No Known Activations