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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating physical movement towards a certain direction

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "over"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lauder
    -0.70
    ãĥ¼ãĥĨãĤ£
    -0.68
    illary
    -0.65
    ORY
    -0.65
    onna
    -0.65
     understatement
    -0.65
    iation
    -0.64
    nesota
    -0.60
    ivity
    -0.60
    oko
    -0.59
    POSITIVE LOGITS
    drive
    1.10
    loading
    0.95
    hang
    0.93
    tones
    0.93
    kill
    0.90
    lord
    0.89
    rule
    0.85
    clock
    0.81
    sold
    0.79
    priced
    0.78
    Act Density 0.066%

    No Known Activations