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

    Neuronpedia

    INDEX
    Explanations

    terms related to decisions, regulations, events, opinions, actions, species, suppliers, questions, applications, processes, sentences, papers, journals, brands, maps, queries, recommendations, important parts of documents, and objects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to important factors in decision-making and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bats
    -0.82
    ooks
    -0.77
    ippers
    -0.76
    ernels
    -0.75
    atives
    -0.71
    iencies
    -0.71
    shirts
    -0.71
     Ladies
    -0.70
    olars
    -0.70
     editions
    -0.69
    POSITIVE LOGITS
    ogram
    0.85
    worker
    0.77
     whose
    0.74
    uble
    0.74
     or
    0.72
     ordinarily
    0.69
    abyte
    0.68
    's
    0.67
     involving
    0.67
     nucleus
    0.66
    Act Density 0.417%

    No Known Activations