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

    Neuronpedia

    INDEX
    Explanations

    specific numbering and labeling within a text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to counting, labeling, or categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dism
    -0.69
     Ukrain
    -0.67
     Tunnel
    -0.65
     Horizon
    -0.64
    anse
    -0.63
     Dough
    -0.63
    olver
    -0.63
     Golem
    -0.61
     Palestin
    -0.61
     Denis
    -0.61
    POSITIVE LOGITS
    otle
    0.79
    emet
    0.79
    rical
    0.78
    cone
    0.77
    achi
    0.76
    ãĥ£
    0.75
    pta
    0.73
    rocal
    0.73
    ļé
    0.73
    iod
    0.71
    Act Density 0.052%

    No Known Activations