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

    Neuronpedia

    INDEX
    Explanations

    actions related to physical movement

    oai_token-act-pair · gpt-3.5-turbo

    actions related to physical movements or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.74
    etheless
    -0.73
     counterpart
    -0.69
     hampered
    -0.67
    yet
    -0.66
     lacking
    -0.65
     territ
    -0.65
    Cub
    -0.65
     lacks
    -0.62
     consequ
    -0.60
    POSITIVE LOGITS
     herself
    0.82
     toilets
    0.80
     knives
    0.79
     needles
    0.72
    ositories
    0.71
    animate
    0.71
    igate
    0.71
     feces
    0.70
     himself
    0.70
    adden
    0.69
    Act Density 0.566%

    No Known Activations