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

    Neuronpedia

    INDEX
    Explanations

    statements of truth or falsity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -1.05
     يتيمه
    -0.88
     pessi
    -0.80
     ejus
    -0.80
     avoient
    -0.80
     Bernadette
    -0.79
     comigo
    -0.79
     ſche
    -0.78
     Jove
    -0.78
    Ivo
    -0.77
    POSITIVE LOGITS
     True
    1.46
     true
    1.46
     TRUE
    1.33
    True
    1.23
     Tru
    1.18
    TRUE
    1.11
    Tru
    1.10
    stdbool
    1.09
    true
    1.02
     truer
    1.02
    Act Density 0.072%

    No Known Activations