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

    Neuronpedia

    INDEX
    Explanations

    names of specific entities (such as newspapers like Daily Express, social media platforms like Twitter, medical conditions like heart disease, minerals like zinc, colors like Turquoise) or keywords related to specific categories (such as social media and check boxes)

    oai_token-act-pair · gpt-3.5-turbo

    references to specific media outlets, geographical locations, and health-related conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ËĪ
    -0.63
    76561
    -0.59
    aband
    -0.52
     Gundam
    -0.50
    aed
    -0.50
     iT
    -0.47
    hematically
    -0.46
    omaly
    -0.46
    lopp
    -0.46
    adobe
    -0.46
    POSITIVE LOGITS
     respectively
    1.66
     alike
    1.64
     depending
    0.81
    depending
    0.77
     versa
    0.75
     thereof
    0.68
    SPONSORED
    0.68
     sectors
    0.64
     interchange
    0.63
     combo
    0.60
    Act Density 0.642%

    No Known Activations