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

    Neuronpedia

    INDEX
    Explanations

    discussions surrounding political ideologies and their social implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by the word "had" or "has"

    np_acts-logits-general · gemini-2.0-flash

    examples and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.65
     poffible
    -0.63
     itſelf
    -0.62
    MigrationBuilder
    -0.61
    UALA
    -0.61
     angekommen
    -0.60
     houſe
    -0.59
     faſt
    -0.59
    UnusedPrivate
    -0.59
     Eſ
    -0.58
    POSITIVE LOGITS
    httphttps
    0.68
     például
    0.68
     famously
    0.60
     misalnya
    0.60
    就是这样
    0.58
     beispielsweise
    0.58
     similarly
    0.57
     example
    0.56
     pourtant
    0.56
    yeur
    0.56
    Act Density 0.723%

    No Known Activations