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

    Neuronpedia

    INDEX
    Explanations

    references to specific events or actions related to rules, regulations, or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ächst
    -0.21
    aeda
    -0.16
    ews
    -0.15
     Creed
    -0.14
    rich
    -0.14
    tg
    -0.14
    eus
    -0.14
    952
    -0.14
    AGO
    -0.14
    egl
    -0.14
    POSITIVE LOGITS
    jes
    0.15
     towards
    0.15
    avern
    0.15
    urma
    0.15
    endum
    0.15
     pedest
    0.15
    oby
    0.14
    ped
    0.14
     cap
    0.14
     COPYING
    0.14
    Act Density 0.171%

    No Known Activations