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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "heard" in various forms or contexts

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

    heard noises and speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mx
    -0.52
     MX
    -0.52
    mX
    -0.51
     Nigel
    -0.49
     cottage
    -0.49
     Lom
    -0.48
     Mog
    -0.48
     Dani
    -0.48
     Lomb
    -0.47
    Formik
    -0.47
    POSITIVE LOGITS
     heard
    1.95
    heard
    1.81
     Heard
    1.65
    Heard
    1.65
     hears
    1.46
     hear
    1.41
     overheard
    1.12
     Hear
    1.09
    hear
    1.09
     hearing
    1.07
    Act Density 0.007%

    No Known Activations