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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific technical terms and URLs

    oai_token-act-pair · gpt-3.5-turbo

    patterns of punctuation and formatting in the text, particularly focusing on the use of commas and other symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.73
     stimulus
    -0.73
    ishment
    -0.71
    ISON
    -0.68
     reinforcement
    -0.67
     descriptor
    -0.66
     itself
    -0.65
    aste
    -0.63
     predictor
    -0.62
    endo
    -0.62
    POSITIVE LOGITS
     Flavoring
    0.98
     Marketable
    0.76
     Deaths
    0.76
     Emer
    0.76
     Bullets
    0.74
    ocr
    0.73
     Diseases
    0.73
     Earthqu
    0.72
     LLC
    0.71
     necks
    0.70
    Act Density 0.596%

    No Known Activations