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

    Neuronpedia

    INDEX
    Explanations

    phrases related to educational settings or classrooms

    oai_token-act-pair · gpt-3.5-turbo

    references to classrooms and educational environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alez
    -0.87
    tale
    -0.81
    omy
    -0.80
    oms
    -0.80
    ulf
    -0.78
    olid
    -0.74
    don
    -0.74
    OD
    -0.73
    oway
    -0.72
    haps
    -0.72
    POSITIVE LOGITS
     walls
    0.82
     entrances
    0.79
     doors
    0.78
     floor
    0.75
     Walls
    0.73
     overflow
    0.73
     corners
    0.72
     stalls
    0.71
     divid
    0.71
    halla
    0.70
    Act Density 0.024%

    No Known Activations