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

    Neuronpedia

    INDEX
    Explanations

    references to waves, often used figuratively to describe a trend or movement

    oai_token-act-pair · gpt-3.5-turbo

    references to waves or surges of various phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ioch
    -0.81
    heid
    -0.77
    nesota
    -0.77
     terrestrial
    -0.75
    rontal
    -0.74
    orate
    -0.72
    mingham
    -0.69
    azeera
    -0.67
    66666666
    -0.66
    chy
    -0.64
    POSITIVE LOGITS
     wave
    1.11
    wave
    0.95
    guide
    0.93
     Wave
    0.86
     waves
    0.82
    crow
    0.81
    brush
    0.76
    pipe
    0.76
    Wave
    0.75
    boat
    0.74
    Act Density 0.007%

    No Known Activations