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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "people" along with related actions or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of groups of people and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Comprehensive
    -0.78
    Effective
    -0.73
    ;;;;;;;;;;;;
    -0.68
     Effective
    -0.67
     Strategy
    -0.65
     Balanced
    -0.64
     Implementation
    -0.64
     modernization
    -0.63
    NES
    -0.63
    ROM
    -0.63
    POSITIVE LOGITS
    folk
    1.07
     nearby
    0.98
    Ĭ±
    0.89
     strangers
    0.86
     gossip
    0.85
     passers
    0.81
     whispering
    0.81
     cheering
    0.80
     alike
    0.80
     clam
    0.79
    Act Density 0.726%

    No Known Activations