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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "the" and its variations

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

    the followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.60
     autorytatywna
    -0.54
     onAnimation
    -0.43
     upraw
    -0.41
     EnglishChoose
    -0.40
    ceğine
    -0.40
     Kohlen
    -0.40
    OGND
    -0.40
     resourceCulture
    -0.39
    InjectAttribute
    -0.39
    POSITIVE LOGITS
     houſe
    0.53
     ſtre
    0.47
     Ganga
    0.44
    ……"
    0.43
     sauce
    0.43
     %.
    0.43
     downvotes
    0.43
    Beat
    0.42
     %).
    0.42
     Constitution
    0.41
    Act Density 0.039%

    No Known Activations