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

    Neuronpedia

    INDEX
    Explanations

    mentions of external entities or locations outside the context described

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "outside."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lda
    -0.74
    Lay
    -0.74
    Percent
    -0.65
    ####
    -0.64
    TER
    -0.64
    cca
    -0.63
    Ly
    -0.63
    ters
    -0.62
    enegger
    -0.62
     Cly
    -0.61
    POSITIVE LOGITS
    etheless
    0.95
    outside
    0.82
    ntil
    0.82
     Indies
    0.77
    assetsadobe
    0.74
     Outside
    0.73
     diameter
    0.70
    Outside
    0.70
    visible
    0.69
    world
    0.69
    Act Density 0.017%

    No Known Activations