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

    Neuronpedia

    INDEX
    Explanations

    phrases that suggest implications or associations about statements and beliefs

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     devenus
    -0.66
    ReusableCell
    -0.66
     becauſe
    -0.65
     ſeveral
    -0.65
    empereur
    -0.62
     whoſe
    -0.62
    IBOutlet
    -0.61
     endregion
    -0.61
     scolaires
    -0.60
     LIRE
    -0.60
    POSITIVE LOGITS
     implies
    0.66
     implying
    0.56
     implied
    0.56
     imply
    0.56
     assumes
    0.50
     implication
    0.50
    opardi
    0.50
     presume
    0.48
     assume
    0.45
     implicitly
    0.45
    Act Density 0.155%

    No Known Activations