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

    Neuronpedia

    INDEX
    Explanations

    terms related to notes or instructions

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases that contain notes or comments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onet
    -0.72
    fu
    -0.70
    rail
    -0.69
     lungs
    -0.67
    lled
    -0.65
    arters
    -0.64
    ãĤ¼ãĤ¦ãĤ¹
    -0.62
     hinge
    -0.61
    stream
    -0.60
    REAM
    -0.59
    POSITIVE LOGITS
     Unsure
    0.72
     Aires
    0.72
     Beware
    0.72
     Remastered
    0.69
    isks
    0.65
     beware
    0.64
     Due
    0.64
     NOTICE
    0.64
     Always
    0.63
     Remember
    0.62
    Act Density 0.090%

    No Known Activations