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

    Neuronpedia

    INDEX
    Explanations

    emotional and opinionated language regarding current events or social issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     incorpor
    -0.72
     clitor
    -0.66
     Mirage
    -0.65
     synerg
    -0.62
     mounts
    -0.61
     perspect
    -0.61
     conduc
    -0.60
     hemor
    -0.59
     partnerships
    -0.59
     Antar
    -0.59
    POSITIVE LOGITS
    ï¸ı
    1.34
    âĶĢâĶĢ
    0.94
    §
    0.87
    ternity
    0.81
    âĸł
    0.77
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.77
    âĤ¬
    0.77
    £
    0.77
    âĶĢâĶĢâĶĢâĶĢ
    0.76
    $
    0.75
    Act Density 0.176%

    No Known Activations