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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expectations, beliefs, and assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.61
    ホ
    -0.47
     som
    -0.45
     aray
    -0.45
    +#+
    -0.44
    種
    -0.43
      
    -0.43
    дзе
    -0.43
     hans
    -0.43
    F
    -0.42
    POSITIVE LOGITS
     likely
    1.06
     Likely
    1.01
    Estimated
    0.99
     expected
    0.98
     estimated
    0.97
    kirakan
    0.95
    Likely
    0.94
    likely
    0.92
    estimated
    0.92
     Estimated
    0.90
    Act Density 0.291%

    No Known Activations