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

    Neuronpedia

    INDEX
    Explanations

    statements that relate to the truth value of propositions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.99
     يتيمه
    -0.95
     Bernadette
    -0.85
    IndentedString
    -0.84
    AnchorStyles
    -0.83
     myſelf
    -0.82
    RectangleBorder
    -0.82
    expandindo
    -0.77
     ſche
    -0.76
     Noche
    -0.75
    POSITIVE LOGITS
     true
    1.96
     True
    1.87
     TRUE
    1.73
    True
    1.69
    TRUE
    1.52
    true
    1.51
     truer
    1.34
     Tru
    1.24
     False
    1.19
    Tru
    1.19
    Act Density 0.058%

    No Known Activations