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

    Neuronpedia

    INDEX
    Explanations

    references to national affiliations or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ory
    -0.17
    gh
    -0.16
    orch
    -0.16
    ors
    -0.15
    se
    -0.15
     nice
    -0.14
    ARI
    -0.14
    ORY
    -0.14
    atur
    -0.14
    ext
    -0.14
    POSITIVE LOGITS
    istic
    0.36
    ities
    0.33
    istically
    0.27
    ized
    0.25
    /local
    0.24
    /reg
    0.24
    izing
    0.24
     anthem
    0.23
    -level
    0.23
    ised
    0.22
    Act Density 0.035%

    No Known Activations