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

    Neuronpedia

    INDEX
    Explanations

    words ending in '-ul' or '-ul' followed by a single digit

    oai_token-act-pair · gpt-3.5-turbo

    words related to a specific element or category, indicating a particular focus on the concept of "ul" or similar terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hitman
    -0.65
     Tables
    -0.61
    PET
    -0.58
     pleas
    -0.58
     Collider
    -0.58
     Mobil
    -0.56
     Clifford
    -0.56
     Beetle
    -0.56
     Cyborg
    -0.56
     Picture
    -0.56
    POSITIVE LOGITS
    monary
    1.28
    terior
    1.05
    iple
    0.95
    esc
    0.92
    gence
    0.90
    indal
    0.88
    uxe
    0.87
    ibrary
    0.87
    aiman
    0.86
    osity
    0.86
    Act Density 0.027%

    No Known Activations