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

    Neuronpedia

    INDEX
    Explanations

    terms related to frequencies or numbers with specific values

    oai_token-act-pair · gpt-3.5-turbo

    terms related to frequency and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zona
    -0.79
    alus
    -0.76
    ovie
    -0.73
    arte
    -0.73
    Reviewed
    -0.69
    ullivan
    -0.69
    wright
    -0.69
    BY
    -0.69
    ermanent
    -0.67
    orned
    -0.67
    POSITIVE LOGITS
     ranges
    1.03
     bands
    0.98
     range
    0.96
     spectrum
    0.94
     amplitude
    0.90
     peaks
    0.89
     modulation
    0.89
     fluctuations
    0.88
     frequencies
    0.87
     oscill
    0.86
    Act Density 0.124%

    No Known Activations