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

    Neuronpedia

    INDEX
    Explanations

    constructs related to single instances or unique entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.99
     StatefulWidget
    -0.73
     Theſe
    -0.71
     linkovi
    -0.70
    цездатний
    -0.68
    Становништво
    -0.65
     }}$}
    -0.65
     يتيمه
    -0.65
    Viungo
    -0.64
     Chriftian
    -0.64
    POSITIVE LOGITS
     single
    0.85
     einzigen
    0.81
     einzige
    0.77
     duy
    0.76
     sole
    0.75
     tunggal
    0.74
     seul
    0.68
     eneste
    0.68
     lone
    0.67
    single
    0.66
    Act Density 0.507%

    No Known Activations