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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparison or rank

    oai_token-act-pair · gpt-3.5-turbo

    references to market tiers and price-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nanto
    -0.63
    ij士
    -0.55
     Kik
    -0.54
    ascus
    -0.53
     nonviolent
    -0.53
     ok
    -0.51
    à¦
    -0.50
     Peng
    -0.50
     detainee
    -0.49
    minster
    -0.47
    POSITIVE LOGITS
     thereof
    1.19
    )!
    1.02
     thereafter
    0.95
     altogether
    0.95
    !).
    0.93
    !)
    0.91
     versa
    0.88
     depending
    0.88
     thereto
    0.86
    )?
    0.85
    Act Density 0.705%

    No Known Activations