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

    Neuronpedia

    INDEX
    Explanations

    references to students

    oai_token-act-pair · gpt-3.5-turbo

    references to students and their activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    neum
    -0.70
    rous
    -0.68
    UTERS
    -0.67
    SHIP
    -0.66
    âĶĢâĶĢâĶĢâĶĢ
    -0.62
     Shack
    -0.61
    SourceFile
    -0.60
     Cape
    -0.59
     bis
    -0.58
    closure
    -0.58
    POSITIVE LOGITS
    hip
    0.91
    girls
    0.86
    uates
    0.85
     enrolled
    0.81
    hips
    0.77
    boys
    0.75
    inary
    0.75
    bridge
    0.73
    eno
    0.73
    '
    0.73
    Act Density 0.055%

    No Known Activations