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

    Neuronpedia

    INDEX
    Explanations

    mentions of students in various educational contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of students

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rous
    -0.68
    UTERS
    -0.65
    neum
    -0.64
     Cape
    -0.63
    ality
    -0.61
     Shack
    -0.60
    âĶĢâĶĢâĶĢâĶĢ
    -0.60
    SHIP
    -0.59
    SourceFile
    -0.59
     compulsion
    -0.57
    POSITIVE LOGITS
    hip
    0.90
     enrolled
    0.80
    girls
    0.79
    uates
    0.79
    '
    0.75
    arate
    0.75
    hips
    0.75
    tu
    0.73
    pace
    0.73
    inary
    0.72
    Act Density 0.050%

    No Known Activations