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

    Neuronpedia

    INDEX
    Explanations

    phrases or words that suggest quotes or attributions in text

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks or special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     recogn
    -0.88
    conservancy
    -0.82
    userc
    -0.76
     pressing
    -0.76
    agate
    -0.75
     manip
    -0.72
     cogn
    -0.71
     ascending
    -0.70
     descending
    -0.69
     recognise
    -0.68
    POSITIVE LOGITS
     Ibid
    0.96
    ————
    0.80
    ONSORED
    0.80
    ————————
    0.78
    rik
    0.77
    Sah
    0.75
    said
    0.74
     Meh
    0.70
    hide
    0.70
    Wilson
    0.70
    Act Density 0.048%

    No Known Activations