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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "hear" and its variations

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

    hear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Formik
    -0.46
     PK
    -0.44
     P
    -0.43
     Egon
    -0.43
     DP
    -0.42
     ex
    -0.42
     Polo
    -0.42
    自
    -0.41
    本
    -0.41
     APS
    -0.41
    POSITIVE LOGITS
     hear
    1.18
     hears
    1.14
    hear
    1.08
     heard
    1.08
    heard
    1.04
    Hear
    1.03
     Hear
    1.01
    Heard
    1.00
     HEAR
    1.00
     Heard
    0.91
    Act Density 0.020%

    No Known Activations