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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize abundance or a significant quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AMA
    -0.62
     immunity
    -0.62
    nings
    -0.62
    endas
    -0.62
     trusts
    -0.61
     belts
    -0.61
    thood
    -0.61
     defends
    -0.61
    uctions
    -0.60
    aughs
    -0.60
    POSITIVE LOGITS
    compatible
    0.70
     wiser
    0.67
     overdue
    0.66
     PIT
    0.66
     reliant
    0.66
    ailable
    0.64
    angered
    0.63
    done
    0.62
    osite
    0.61
    lier
    0.61
    Act Density 0.378%

    No Known Activations