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

    Neuronpedia

    INDEX
    Explanations

    words starting with "sw" or similar patterns

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "news."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     PLAN
    -0.70
    chell
    -0.67
     caution
    -0.67
     cloves
    -0.64
     Centauri
    -0.63
     flares
    -0.63
     crush
    -0.63
     secretive
    -0.62
     restraining
    -0.62
     partial
    -0.61
    POSITIVE LOGITS
    ifty
    1.09
    athed
    1.07
    ift
    1.05
    addle
    1.04
    imming
    1.04
    ollen
    1.02
    atches
    1.01
    itched
    1.00
    arf
    0.97
    arer
    0.95
    Act Density 0.008%

    No Known Activations