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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs in statements about knowledge or actions taken

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a state of being, change, or needs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gart
    -0.87
    bush
    -0.78
    nels
    -0.77
     heels
    -0.72
    chairs
    -0.68
     IDs
    -0.67
    elist
    -0.63
    edin
    -0.63
     IMAGES
    -0.63
    chains
    -0.62
    POSITIVE LOGITS
     learned
    0.94
     learnt
    0.93
     transpired
    0.86
     glean
    0.84
     happening
    0.84
     gained
    0.83
     accomplished
    0.79
     done
    0.79
     changed
    0.76
     achieved
    0.73
    Act Density 0.107%

    No Known Activations