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

    Neuronpedia

    INDEX
    Explanations

    regions and historical political entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.84
    featureID
    -0.81
    Personendaten
    -0.77
    iſchen
    -0.75
    RegressionTest
    -0.75
    aarrggbb
    -0.73
     contextLoads
    -0.72
    <unused8>
    -0.72
    [@BOS@]
    -0.71
    <unused79>
    -0.71
    POSITIVE LOGITS
     convinced
    0.28
     Kruse
    0.28
     Stadtteil
    0.28
     McGowan
    0.25
    监
    0.25
    这对
    0.24
    至於
    0.23
    至于
    0.23
     języka
    0.23
     Küsten
    0.23
    Act Density 0.987%

    No Known Activations