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

    Neuronpedia

    INDEX
    Explanations

    phrases related to competence and professionalism

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to talent and interpersonal skills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ormon
    -0.81
    DragonMagazine
    -0.76
    classified
    -0.73
    sson
    -0.70
    é¾į
    -0.70
    alia
    -0.66
    rolet
    -0.66
    lez
    -0.65
    trak
    -0.65
    ormons
    -0.65
    POSITIVE LOGITS
     himself
    0.94
     effortlessly
    0.90
     stride
    0.86
     subordinates
    0.84
     mischief
    0.78
     enthus
    0.78
     everything
    0.78
     instinctively
    0.77
     Himself
    0.76
     witty
    0.75
    Act Density 0.721%

    No Known Activations