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

    Neuronpedia

    INDEX
    Explanations

    terms related to the concept of "normal."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elic
    -0.18
    erior
    -0.17
    lint
    -0.17
    isoft
    -0.16
    ernet
    -0.16
    eling
    -0.15
    undry
    -0.15
    inous
    -0.15
    ernaut
    -0.15
    ary
    -0.15
    POSITIVE LOGITS
    cy
    0.45
    ised
    0.33
    izing
    0.30
    izedName
    0.29
    mente
    0.28
    isation
    0.26
    ity
    0.25
    ising
    0.25
    izer
    0.25
    cies
    0.25
    Act Density 0.027%

    No Known Activations