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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating specific evidence or support for claims

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     propOrder
    -0.66
     plotly
    -0.55
    cipe
    -0.52
    ()];
    -0.52
     Meyer
    -0.52
    newData
    -0.52
    }*/
    -0.51
    ímite
    -0.49
    iern
    -0.48
    んだけど
    -0.48
    POSITIVE LOGITS
    PerformLayout
    0.73
     <=",
    0.66
     entgegen
    0.62
    AccessorTable
    0.61
    CloseOperation
    0.61
     phyto
    0.59
     plagio
    0.59
    Tikang
    0.58
    haustible
    0.58
    EndGlobalSection
    0.58
    Act Density 0.019%

    No Known Activations