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

    Neuronpedia

    INDEX
    Explanations

    actions and responses related to obedience and submission

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

    actions completed or in progress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.74
     kasarigan
    -0.71
     protoimpl
    -0.68
    MigrationBuilder
    -0.63
     poveznice
    -0.63
    ьаж
    -0.62
    Chham
    -0.60
    :+:
    -0.58
    Derbyniad
    -0.58
     linkovi
    -0.57
    POSITIVE LOGITS
     assisted
    0.34
     Streifen
    0.31
    assisted
    0.30
     troca
    0.30
     covered
    0.29
     nächsten
    0.29
     året
    0.29
    いった
    0.28
     accordingly
    0.28
    dummy
    0.27
    Act Density 0.072%

    No Known Activations