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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "beat" with varying contexts

    oai_token-act-pair · gpt-3.5-turbo

    the word "beat" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orrow
    -0.81
    isal
    -0.74
    isse
    -0.74
    ateral
    -0.73
    amera
    -0.69
    pmwiki
    -0.68
    arger
    -0.67
    Austral
    -0.67
     facult
    -0.66
    agher
    -0.66
    POSITIVE LOGITS
    beat
    1.06
    down
    1.01
    boxing
    0.91
    tle
    0.87
    nik
    0.85
    sticks
    0.83
    downs
    0.80
    Beat
    0.79
     beat
    0.78
    ingly
    0.77
    Act Density 0.025%

    No Known Activations