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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "going over" something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "over"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ï¸
    -0.78
    iation
    -0.72
     Lauder
    -0.72
    illary
    -0.68
    ãĥ¼ãĥĨãĤ£
    -0.67
    iosity
    -0.66
    ¯¯¯¯
    -0.65
    Motion
    -0.64
    ivity
    -0.63
    anto
    -0.62
    POSITIVE LOGITS
    drive
    0.93
    haul
    0.92
    mast
    0.86
    whel
    0.86
    tones
    0.85
    loading
    0.81
    whelming
    0.79
    priced
    0.75
    rish
    0.72
    awed
    0.71
    Act Density 0.042%

    No Known Activations