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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the use of something for a specific purpose

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the various uses of resources or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    beat
    -0.86
    ellen
    -0.78
    edin
    -0.73
    uckland
    -0.72
    ieties
    -0.70
    iev
    -0.70
    rose
    -0.68
    pour
    -0.68
     Rebell
    -0.67
    umar
    -0.66
    POSITIVE LOGITS
     purposes
    1.32
    geries
    0.98
     debugging
    0.98
     emergencies
    0.97
     convenience
    0.97
    aging
    0.96
     storing
    0.95
     authentication
    0.95
     constructing
    0.94
    gery
    0.92
    Act Density 0.133%

    No Known Activations