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

    Neuronpedia

    INDEX
    Explanations

    words related to deception or manipulation strategies

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

    Follows "been," "is," "was," or "be"

    np_acts-logits-general · gemini-2.0-flash

    verb "to be" followed by states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     works
    -0.47
     ajuns
    -0.47
    processData
    -0.44
    Up
    -0.43
    ContentAsync
    -0.43
     sucedido
    -0.42
     values
    -0.42
     valores
    -0.42
    todoList
    -0.42
     crescimento
    -0.41
    POSITIVE LOGITS
     ActionBar
    0.63
    ()]);
    0.62
    Hauptartikel
    0.62
    Papers
    0.61
    desertcart
    0.60
    spreis
    0.57
     gainera
    0.57
    IntoConstraints
    0.56
    fillType
    0.56
     unknownFields
    0.56
    Act Density 0.308%

    No Known Activations