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

    Neuronpedia

    INDEX
    Explanations

    references to central authority or centralized systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RIORITY
    -0.17
    arest
    -0.16
    ollen
    -0.15
    off
    -0.14
    dna
    -0.14
    ertino
    -0.14
    ecs
    -0.14
    esel
    -0.14
    ">//
    -0.13
    ktor
    -0.13
    POSITIVE LOGITS
    most
    0.21
    -central
    0.21
    ised
    0.20
    ities
    0.19
    ized
    0.17
    core
    0.16
    cott
    0.16
    ization
    0.16
    ize
    0.16
    lake
    0.15
    Act Density 0.020%

    No Known Activations