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

    Neuronpedia

    INDEX
    Explanations

    specific patterns of text related to order, ranking, and magnitude

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the term "order of" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    catch
    -0.78
    gow
    -0.72
    gae
    -0.71
    ished
    -0.70
    owler
    -0.70
    touch
    -0.68
    gre
    -0.67
    atform
    -0.66
    icket
    -0.65
    ipel
    -0.64
    POSITIVE LOGITS
     approvals
    0.73
    MX
    0.67
    SpaceEngineers
    0.66
     magnitude
    0.65
     chanting
    0.64
     keys
    0.64
    arez
    0.63
     congr
    0.62
    odan
    0.62
    udo
    0.61
    Act Density 0.210%

    No Known Activations