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

    Neuronpedia

    INDEX
    Explanations

    references to students or educational settings

    oai_token-act-pair · gpt-3.5-turbo

    references to students and their activities or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¢
    -0.71
    neum
    -0.70
    SourceFile
    -0.69
    UTERS
    -0.63
     Bots
    -0.62
    stros
    -0.61
    ãģ®å
    -0.60
     bis
    -0.59
    rous
    -0.59
     Shack
    -0.58
    POSITIVE LOGITS
     enrolled
    1.08
     tuition
    1.02
     graduating
    0.95
    uates
    0.95
     dorm
    0.89
    Students
    0.89
     graduate
    0.88
    girls
    0.88
     graduates
    0.86
    bridge
    0.86
    Act Density 0.041%

    No Known Activations