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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to individuals and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     utr
    -0.82
    MethodManager
    -0.81
     nahilalakip
    -0.80
     lenker
    -0.78
     Guter
    -0.76
    jooq
    -0.75
    mtrl
    -0.75
    ovas
    -0.73
    CharStream
    -0.72
     Hof
    -0.71
    POSITIVE LOGITS
     éc
    0.88
    Felix
    0.78
     Heuer
    0.78
     Whipple
    0.77
     Felix
    0.75
     calcite
    0.72
     Gaj
    0.72
     Zit
    0.71
     Energi
    0.71
     Marlin
    0.71
    Act Density 1.585%

    No Known Activations