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

    Neuronpedia

    INDEX
    Explanations

    temporal markers and references to time

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

    after conjunction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.91
    <unused16>
    -0.78
    <unused41>
    -0.78
    <unused14>
    -0.78
    <unused23>
    -0.78
    [@BOS@]
    -0.78
    <unused51>
    -0.78
    <unused43>
    -0.77
    <unused42>
    -0.77
    <unused8>
    -0.77
    POSITIVE LOGITS
     diper
    0.31
    After
    0.31
    詳細は
    0.31
     viss
    0.31
     graciously
    0.31
     ли
    0.30
     After
    0.30
     quedado
    0.30
    Info
    0.30
     được
    0.30
    Act Density 0.005%

    No Known Activations