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

    Neuronpedia

    INDEX
    Explanations

    words related to ranking or importance

    oai_token-act-pair · gpt-3.5-turbo

    words related to performance and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     waivers
    -0.72
     Consent
    -0.71
     designation
    -0.70
     Dragons
    -0.69
     Generator
    -0.66
     Jackets
    -0.65
     Prevention
    -0.64
     Knights
    -0.64
     Waves
    -0.63
     Writers
    -0.63
    POSITIVE LOGITS
    erous
    1.18
    istent
    1.11
    fficient
    1.09
    isable
    1.09
    istic
    1.08
    ulent
    1.07
    ensical
    1.06
    icky
    1.03
    ceptive
    1.02
    hesive
    1.01
    Act Density 0.343%

    No Known Activations