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

    Neuronpedia

    INDEX
    Explanations

    adjectives ending in 'ing'

    oai_token-act-pair · gpt-3.5-turbo

    present participles or gerunds indicating ongoing actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    paying
    -0.92
    thodox
    -0.88
    saf
    -0.84
    aligned
    -0.83
    correct
    -0.81
    chery
    -0.81
    pees
    -0.80
    TRY
    -0.78
    ternity
    -0.77
    itism
    -0.76
    POSITIVE LOGITS
     tide
    0.96
     sands
    0.91
     tides
    0.86
     sea
    0.86
     masses
    0.84
     wreckage
    0.84
     hearts
    0.81
     footsteps
    0.79
     waters
    0.79
     jaws
    0.78
    Act Density 0.139%

    No Known Activations