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

    Neuronpedia

    INDEX
    Explanations

    words related to dirtiness or decay

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "gr."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phrine
    -0.85
    )=(
    -0.77
    vention
    -0.74
    hibition
    -0.69
    ership
    -0.69
    manship
    -0.66
    âĹ¼
    -0.66
    ezvous
    -0.65
    PORT
    -0.65
    idas
    -0.65
    POSITIVE LOGITS
    udge
    1.20
    umpy
    1.18
    udging
    1.16
    aciously
    1.15
    iffin
    1.07
    inder
    1.01
    iddle
    1.00
    ained
    1.00
    iddles
    0.98
    ubb
    0.98
    Act Density 0.009%

    No Known Activations