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

    Neuronpedia

    INDEX
    Explanations

    mentions or instances of the word "model."

    oai_token-act-pair · gpt-3.5-turbo

    references to different models or frameworks in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulhu
    -0.88
    azar
    -0.83
    omen
    -0.75
    OME
    -0.72
    kefeller
    -0.70
    cyclopedia
    -0.70
    entimes
    -0.70
    hedon
    -0.68
    pin
    -0.68
    èª
    -0.68
    POSITIVE LOGITS
     organism
    0.97
    ered
    0.77
    model
    0.76
    models
    0.75
     organisms
    0.74
     Penal
    0.70
     Mayhem
    0.69
    etter
    0.68
     Operator
    0.67
    er
    0.67
    Act Density 0.031%

    No Known Activations