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

    Neuronpedia

    INDEX
    Explanations

    references to the character "Alice" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the name "Alice" mentioned in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.90
    ework
    -0.77
    restling
    -0.72
    soDeliveryDate
    -0.71
    eling
    -0.71
    aments
    -0.71
    ODUCT
    -0.71
    orship
    -0.69
    rontal
    -0.69
    eful
    -0.67
    POSITIVE LOGITS
     Wonderland
    0.85
     Springs
    0.83
     Cooper
    0.81
     Walton
    0.76
    que
    0.73
    querade
    0.71
    Alice
    0.71
    udi
    0.70
    uria
    0.69
     Bailey
    0.68
    Act Density 0.040%

    No Known Activations