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

    Neuronpedia

    INDEX
    Explanations

    descriptions emphasizing details and specifics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thood
    -0.89
    perse
    -0.81
    leground
    -0.77
    Scotland
    -0.73
    ����
    -0.72
    ashington
    -0.71
    minent
    -0.70
    ée
    -0.69
    uclear
    -0.69
    ictional
    -0.67
    POSITIVE LOGITS
     downside
    1.30
    oret
    1.29
     biggest
    1.21
     easiest
    1.15
     simplest
    1.13
     sheer
    1.12
     coolest
    1.09
     cheapest
    1.08
     drawback
    1.07
     slightest
    1.07
    Act Density 0.350%

    No Known Activations