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

    Neuronpedia

    INDEX
    Explanations

    phrases related to urban infrastructure

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns and terms related to various physical objects, conditions, and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įå
    -0.76
    Versions
    -0.70
    ãĥ´
    -0.69
    ãĥĥãĥī
    -0.63
    ãĤ¤ãĥĪ
    -0.61
    ãģĦ
    -0.59
    alle
    -0.59
    userc
    -0.58
    76561
    -0.58
    姫
    -0.57
    POSITIVE LOGITS
    ¶
    0.60
    ↵
    0.58
     (
    0.54
     ('
    0.53
     teamed
    0.53
     (£
    0.52
    ↵↵
    0.51
     Belfast
    0.51
     (?,
    0.50
     aka
    0.50
    Act Density 0.603%

    No Known Activations