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

    Neuronpedia

    INDEX
    Explanations

    processes and actions related to decision making and problem solving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     of
    -0.59
     am
    -0.54
     a
    -0.52
     an
    -0.51
     
    -0.51
     H
    -0.50
     his
    -0.49
     dis
    -0.48
     A
    -0.47
     E
    -0.46
    POSITIVE LOGITS
     Efq
    1.02
    ſelf
    0.89
     purpoſe
    0.88
    ſelves
    0.88
     itſelf
    0.87
     Majefty
    0.86
     myſelf
    0.86
    queryInterface
    0.84
    NOPQRST
    0.83
     Monfieur
    0.82
    Act Density 0.696%

    No Known Activations