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

    Neuronpedia

    INDEX
    Explanations

    long complex words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    quantitative assessments of social or economic conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Maps
    -0.82
    Camera
    -0.78
    Ä
    -0.76
    CD
    -0.76
    AG
    -0.75
     Documents
    -0.74
    Call
    -0.73
    Ag
    -0.72
    Gab
    -0.72
    Jar
    -0.71
    POSITIVE LOGITS
     supra
    0.82
    anwhile
    0.80
     overpowered
    0.75
     undecided
    0.73
     extinct
    0.72
     intrusive
    0.71
     unrem
    0.71
     upt
    0.71
     forbidden
    0.70
     optional
    0.70
    Act Density 0.440%

    No Known Activations