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

    Neuronpedia

    INDEX
    Explanations

    references to philosophical concepts and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ContentAsync
    -0.63
    StreetMap
    -0.62
     ModelExpression
    -0.56
     eccell
    -0.55
     superstitious
    -0.54
     المعيارى
    -0.53
    mbggenerated
    -0.52
    TypedDataSet
    -0.52
     lành
    -0.52
    écution
    -0.52
    POSITIVE LOGITS
     philosophers
    0.90
     philosophical
    0.85
     philosopher
    0.84
    philosop
    0.79
     thinkers
    0.73
     philosoph
    0.70
     filosof
    0.67
     thinker
    0.66
     philosophy
    0.64
     Plato
    0.63
    Act Density 0.819%

    No Known Activations