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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names of people and places

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     estimating
    -0.60
     embassies
    -0.58
     ENTER
    -0.57
     tape
    -0.57
     pause
    -0.56
    bre
    -0.56
    aer
    -0.56
     biologists
    -0.56
     Ec
    -0.56
     MIC
    -0.55
    POSITIVE LOGITS
    ussion
    0.70
    ilyn
    0.69
    accompan
    0.68
    atre
    0.67
    âķIJ
    0.66
    Fan
    0.66
    Versions
    0.65
    ModLoader
    0.65
    vals
    0.65
    ¨
    0.64
    Act Density 0.592%

    No Known Activations