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
     Cad
    -0.16
     cad
    -0.15
     Dat
    -0.15
    imming
    -0.15
    Cad
    -0.14
     delegate
    -0.14
    nul
    -0.14
    iges
    -0.14
     dracon
    -0.14
     anecd
    -0.14
    POSITIVE LOGITS
     philosophy
    0.52
     Philosophy
    0.52
    phil
    0.49
     philosophers
    0.49
     philosophical
    0.48
     Philosoph
    0.47
     philosopher
    0.46
     philosoph
    0.42
    Phil
    0.42
    åĵ²
    0.42
    Act Density 0.038%

    No Known Activations