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

    Neuronpedia

    INDEX
    Explanations

    mentions of elevators and related activities or features

    oai_token-act-pair · gpt-3.5-turbo

    terms related to elevators and elevation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vous
    -0.82
    nia
    -0.81
    ned
    -0.80
    ters
    -0.76
    ãģ¦
    -0.75
    fulness
    -0.74
    neg
    -0.72
    cheat
    -0.71
    nar
    -0.70
    kered
    -0.70
    POSITIVE LOGITS
     elev
    0.95
     heights
    0.94
     shaft
    0.88
     ceilings
    0.86
     Everest
    0.83
     elevation
    0.80
     elevate
    0.76
    ipl
    0.75
    uations
    0.75
    xual
    0.75
    Act Density 0.075%

    No Known Activations