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

    Neuronpedia

    INDEX
    Explanations

    return statements and related return values within function definitions

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

    Code snippets with function calls or variable assignments

    np_acts-logits-general · gemini-2.0-flash

    consequently

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused52>
    -1.26
    <unused23>
    -1.26
    [@BOS@]
    -1.25
    <unused8>
    -1.25
    <unused42>
    -1.25
    <unused43>
    -1.25
    <unused41>
    -1.25
    <unused28>
    -1.25
    <unused14>
    -1.25
    <unused16>
    -1.25
    POSITIVE LOGITS
     donc
    0.42
     therefore
    0.38
     thus
    0.32
     hence
    0.28
    จึง
    0.27
     więc
    0.27
    Therefore
    0.26
     then
    0.24
     quindi
    0.24
     Therefore
    0.24
    Act Density 0.179%

    No Known Activations