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

    Neuronpedia

    INDEX
    Explanations

    mentions of group members or individuals within a specific context

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or groups associated with membership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    forest
    -0.72
    bows
    -0.70
     Pwr
    -0.68
    trop
    -0.67
    TI
    -0.64
     Situation
    -0.64
    anche
    -0.64
     Tropical
    -0.63
    Bear
    -0.63
    Sharp
    -0.62
    POSITIVE LOGITS
    hips
    1.34
    hip
    1.02
    member
    0.91
    cius
    0.90
    doms
    0.86
     members
    0.80
    members
    0.79
     member
    0.78
    */(
    0.76
     dues
    0.76
    Act Density 0.035%

    No Known Activations