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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "recording" and its variations

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

    recording

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AttributeSet
    -0.59
    But
    -0.50
     simpto
    -0.50
     Wis
    -0.47
     onOptions
    -0.46
    Wis
    -0.45
     circumstantial
    -0.44
    5
    -0.44
    mites
    -0.43
    affaire
    -0.43
    POSITIVE LOGITS
     recording
    1.78
     Recording
    1.78
    Recording
    1.73
    recording
    1.66
     RECORDING
    1.60
     recordings
    1.56
     Recordings
    1.47
     recorded
    1.11
    recorded
    1.11
     Recorded
    1.06
    Act Density 0.008%

    No Known Activations