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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions involving physical transformation or modification

    oai_token-act-pair · gpt-3.5-turbo

    actions or processes related to various forms of treatment or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.68
    intent
    -0.68
    argument
    -0.62
    reporting
    -0.61
    âĹ¼
    -0.61
    antics
    -0.60
    taboola
    -0.60
    smoking
    -0.59
     pleading
    -0.59
    ":"/
    -0.58
    POSITIVE LOGITS
     everything
    0.79
     portions
    0.78
     them
    0.75
     vegetables
    0.71
     anew
    0.71
     entire
    0.70
     your
    0.69
     oneself
    0.69
     sidewalks
    0.68
     buildings
    0.68
    Act Density 0.354%

    No Known Activations