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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of normalcy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erior
    -0.19
    undry
    -0.18
    ernaut
    -0.16
    ernet
    -0.16
    isoft
    -0.16
    ary
    -0.15
    eling
    -0.15
    elic
    -0.15
    orse
    -0.15
    lint
    -0.15
    POSITIVE LOGITS
    cy
    0.43
    ised
    0.32
    izedName
    0.29
    mente
    0.28
    izing
    0.27
    cies
    0.25
    isation
    0.25
    izer
    0.25
    ise
    0.24
    ity
    0.24
    Act Density 0.022%

    No Known Activations