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

    Neuronpedia

    INDEX
    Explanations

    directional terms related to positioning or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Left or Right

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     left
    -0.43
     vacation
    -0.43
     owner
    -0.42
     today
    -0.42
     ladies
    -0.42
     jury
    -0.41
     spoiler
    -0.41
    ษา
    -0.41
    notated
    -0.41
     cowardly
    -0.41
    POSITIVE LOGITS
     Right
    1.44
    Right
    1.40
     Rights
    1.01
    Left
    0.90
    Rights
    0.84
    RIGHT
    0.79
     Left
    0.76
     Righ
    0.76
     RIGHT
    0.73
     Direito
    0.73
    Act Density 0.006%

    No Known Activations