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

    Neuronpedia

    INDEX
    Explanations

    words related to water movement or disturbance, particularly waves

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of waves, including sound waves and ocean waves

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ioch
    -0.74
    isma
    -0.70
    orate
    -0.70
    aples
    -0.68
     proc
    -0.68
    uments
    -0.65
    ria
    -0.65
    rax
    -0.64
     reason
    -0.64
     purpose
    -0.62
    POSITIVE LOGITS
     waves
    1.32
    waves
    1.29
     Waves
    1.07
     wave
    1.04
    wave
    1.03
    hower
    0.99
     Wave
    0.96
    hips
    0.85
    guide
    0.85
    imilar
    0.82
    Act Density 0.009%

    No Known Activations