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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships in complex statements

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

    preceding logical connectors

    np_acts-logits-general · gemini-2.0-flash

    logical consequence or relation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    %")
    -0.81
    `,
    -0.69
    {}",
    -0.68
     nakalista
    -0.68
    :✨
    -0.65
    \"]
    -0.65
    %");
    -0.65
    /$',
    -0.65
    %</
    -0.64
    "],
    -0.64
    POSITIVE LOGITS
     therefore
    2.32
     hence
    2.18
     thus
    2.10
     consequently
    2.00
    therefore
    1.87
    hence
    1.80
     thereby
    1.79
    thus
    1.69
     therefor
    1.64
     portanto
    1.58
    Act Density 0.473%

    No Known Activations