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

    Neuronpedia

    INDEX
    Explanations

    references to national organizations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ory
    -0.19
    ORY
    -0.17
    ember
    -0.16
    зи
    -0.16
    nice
    -0.15
    se
    -0.15
     nice
    -0.15
    d
    -0.15
    thing
    -0.14
    eka
    -0.14
    POSITIVE LOGITS
    ized
    0.25
    istic
    0.24
    ities
    0.24
    izing
    0.24
    /local
    0.22
    /global
    0.22
    /state
    0.20
    ization
    0.20
    -level
    0.20
    ixe
    0.20
    Act Density 0.037%

    No Known Activations