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

    Neuronpedia

    INDEX
    Explanations

    words that indicate comfort or simplicity in processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Internet
    -0.63
     raiſ
    -0.60
     uſed
    -0.58
    OGND
    -0.56
     OMITBAD
    -0.56
     occaf
    -0.55
     faſt
    -0.55
    StreetMap
    -0.55
     queſta
    -0.55
     getAddress
    -0.54
    POSITIVE LOGITS
    Column
    0.52
     Column
    0.50
     specialises
    0.50
     pillars
    0.49
     pillar
    0.49
     specialise
    0.49
    Situated
    0.48
    Located
    0.48
     pilares
    0.48
     specialising
    0.47
    Act Density 0.165%

    No Known Activations