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

    Neuronpedia

    INDEX
    Explanations

    mention of statistical methodologies and causal inference concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -1.20
    GEBURTSDATUM
    -0.98
    MLLoader
    -0.97
    queryInterface
    -0.95
     Италијани
    -0.93
     myſelf
    -0.87
     poffible
    -0.86
     ―――――
    -0.84
     pinulongan
    -0.83
     greateſt
    -0.82
    POSITIVE LOGITS
    <eos>
    0.57
    ,
    0.55
    ad
    0.54
    a
    0.53
     
    0.52
    .
    0.48
    ch
    0.46
    b
    0.46
    if
    0.44
    hu
    0.44
    Act Density 0.556%

    No Known Activations