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

    Neuronpedia

    INDEX
    Explanations

    words related to actions or processes ending in 'ing'

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and present participles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cmp
    -0.73
    umm
    -0.64
    ère
    -0.64
     cheating
    -0.63
    bet
    -0.62
     spitting
    -0.62
    ternity
    -0.61
    omet
    -0.61
    fulness
    -0.59
    igne
    -0.59
    POSITIVE LOGITS
    redients
    0.93
    tons
    0.86
     Advice
    0.85
     Appro
    0.81
     Thoughts
    0.81
     Details
    0.80
     Concepts
    0.79
     Factors
    0.78
     Pitch
    0.78
    assis
    0.77
    Act Density 0.166%

    No Known Activations