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

    Neuronpedia

    INDEX
    Explanations

    specific proper nouns and phrases related to locations or identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sbericht
    -0.43
     Sin
    -0.40
     Mother
    -0.38
    ImageList
    -0.38
     slide
    -0.36
     Mir
    -0.36
     Random
    -0.35
     Shams
    -0.35
     South
    -0.35
     Kind
    -0.35
    POSITIVE LOGITS
     defaultstate
    0.83
    FormTagHelper
    0.62
    AccessorTable
    0.56
     muscles
    0.54
    Chham
    0.48
     Muscles
    0.48
    andExpect
    0.48
     TextAppearance
    0.47
     toxicity
    0.47
     músculos
    0.46
    Act Density 1.517%

    No Known Activations