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

    Neuronpedia

    INDEX
    Explanations

    references to progress or improvement

    oai_token-act-pair · gpt-3.5-turbo

    references to progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ENA
    -0.73
     Peninsula
    -0.67
     gorge
    -0.64
     duck
    -0.62
     ski
    -0.61
     resorts
    -0.61
    Natural
    -0.60
    FACE
    -0.60
     cust
    -0.59
    stal
    -0.59
    POSITIVE LOGITS
    ivism
    1.40
    iveness
    1.12
    ivity
    1.09
    ives
    1.07
    ions
    1.06
    ivist
    1.03
     progress
    0.95
    ively
    0.91
    ments
    0.90
     Progress
    0.89
    Act Density 0.016%

    No Known Activations