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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to people and places

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "rich."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ŃĶ
    -0.80
    FY
    -0.74
    IENCE
    -0.71
    SCP
    -0.67
     Carry
    -0.63
    WAYS
    -0.63
     Cortex
    -0.63
    âĹ¼
    -0.63
    Ĥİ
    -0.62
     Kinnikuman
    -0.61
    POSITIVE LOGITS
    rich
    1.05
    mond
    0.99
    hardt
    0.99
    ards
    0.97
    ard
    0.93
    eton
    0.92
    ulas
    0.87
    lings
    0.86
    fried
    0.84
    heid
    0.84
    Act Density 0.005%

    No Known Activations