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

    Neuronpedia

    INDEX
    Explanations

    references to software add-ons or extensions

    oai_token-act-pair · gpt-3.5-turbo

    references to add-ons and additional features related to software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Liberties
    -0.72
     Chambers
    -0.64
    ãĥ£
    -0.63
     Bast
    -0.59
    Ń·
    -0.59
     closely
    -0.58
     Desert
    -0.57
     Beautiful
    -0.56
     Fires
    -0.55
     chronically
    -0.55
    POSITIVE LOGITS
    ons
    1.22
    on
    1.10
    ins
    1.05
    ONS
    0.92
    your
    0.91
    factor
    0.89
    service
    0.88
    route
    0.88
    advertising
    0.86
    in
    0.86
    Act Density 0.043%

    No Known Activations