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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "normal" or standards of normalcy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erior
    -0.18
    ernaut
    -0.17
    undry
    -0.17
    ERN
    -0.17
    ernet
    -0.16
    ary
    -0.15
    ipro
    -0.15
    orse
    -0.15
    frauen
    -0.15
    edb
    -0.15
    POSITIVE LOGITS
    cy
    0.41
    ised
    0.29
    mente
    0.27
    izedName
    0.26
    izing
    0.26
    ity
    0.25
    isation
    0.24
    cies
    0.23
    ising
    0.23
    izer
    0.23
    Act Density 0.024%

    No Known Activations