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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to physical movement or change in location, particularly involving some form of action

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    illary
    -0.75
    ãĥ¼ãĥĨãĤ£
    -0.70
     understatement
    -0.70
    ivity
    -0.66
    ï¸
    -0.66
    iation
    -0.65
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -0.64
    onna
    -0.64
    ORY
    -0.64
    uum
    -0.63
    POSITIVE LOGITS
    loading
    1.10
    tones
    1.09
    drive
    1.09
    hang
    1.08
    lord
    1.05
    rule
    0.95
    kill
    0.90
    sold
    0.88
    haul
    0.87
    reaching
    0.86
    Act Density 0.103%

    No Known Activations