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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "examine" and its variants

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

    the act of examining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.89
     queſta
    -0.84
    <pad>
    -0.77
    <unused68>
    -0.77
    <unused42>
    -0.77
    <unused41>
    -0.77
    <unused14>
    -0.77
    <unused51>
    -0.76
    <unused43>
    -0.76
    <unused28>
    -0.76
    POSITIVE LOGITS
     examine
    1.02
     Examine
    1.00
     examination
    0.96
     examining
    0.92
    Examine
    0.91
     examined
    0.91
     EXAMIN
    0.88
     Examination
    0.84
    examine
    0.84
     Examining
    0.83
    Act Density 0.020%

    No Known Activations