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

    Neuronpedia

    INDEX
    Explanations

    various associations and organizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific associations and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     paradise
    -0.79
     havoc
    -0.78
     sanity
    -0.78
    stakes
    -0.72
     temptation
    -0.70
     dilemma
    -0.70
     wre
    -0.68
    tty
    -0.67
     nuance
    -0.65
     flaw
    -0.65
    POSITIVE LOGITS
     Chiefs
    1.17
     Colleges
    1.07
     Manufact
    1.02
     Journalists
    1.01
     Teachers
    1.01
     Prosecut
    0.99
     Professional
    0.97
     Colleg
    0.96
     Architects
    0.95
     Physicians
    0.93
    Act Density 0.047%

    No Known Activations