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

    Neuronpedia

    INDEX
    Explanations

    references to different models or versions of products

    oai_token-act-pair · gpt-3.5-turbo

    references to different models of a product

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vernment
    -1.00
    olulu
    -0.84
    ulhu
    -0.82
    usters
    -0.80
    tein
    -0.80
    kefeller
    -0.76
    azar
    -0.74
    cffff
    -0.73
    arching
    -0.72
    olkien
    -0.71
    POSITIVE LOGITS
    model
    0.96
     Models
    0.81
    Versions
    0.79
     models
    0.79
     model
    0.78
     Model
    0.76
    maker
    0.70
    urer
    0.70
    models
    0.70
     Penal
    0.69
    Act Density 0.020%

    No Known Activations