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

    Neuronpedia

    INDEX
    Explanations

    indicators of verification and confirmation in discussions

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

    Confirmation or verification

    np_acts-logits-general · gemini-2.0-flash

    confirming facts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.95
     autorytatywna
    -0.89
     queſta
    -0.88
    ロウィン
    -0.80
    <unused47>
    -0.78
    <unused41>
    -0.78
    <unused14>
    -0.78
    <unused16>
    -0.78
    <unused8>
    -0.78
    <unused3>
    -0.78
    POSITIVE LOGITS
     confirm
    0.43
     confirmation
    0.39
    confirm
    0.35
     confirmer
    0.34
     confirmed
    0.33
     confir
    0.33
     C
    0.32
     confirma
    0.32
     i
    0.31
    C
    0.31
    Act Density 0.751%

    No Known Activations