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

    Neuronpedia

    INDEX
    Explanations

    non-standard or special characters like 'Ċ'

    oai_token-act-pair · gpt-3.5-turbo

    legal terminology and references related to court proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uph
    -0.68
    lihood
    -0.68
     Machina
    -0.68
    EStream
    -0.65
     dissu
    -0.65
     citiz
    -0.64
     err
    -0.62
     reneg
    -0.62
     downhill
    -0.62
     Xia
    -0.61
    POSITIVE LOGITS
    Interested
    0.85
    Specifically
    0.79
    WASHINGTON
    0.74
    KR
    0.72
    ORE
    0.67
    FIN
    0.67
    Known
    0.65
    Fair
    0.65
    Their
    0.65
    Published
    0.65
    Act Density 0.164%

    No Known Activations