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

    Neuronpedia

    INDEX
    Explanations

    references to the United States and its political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gressor
    -0.15
    esi
    -0.15
    ouch
    -0.15
    INDER
    -0.14
    apo
    -0.14
    ket
    -0.13
     nominal
    -0.13
     Heller
    -0.13
     Trap
    -0.13
     Sed
    -0.13
    POSITIVE LOGITS
    eya
    0.17
    enson
    0.17
    aina
    0.15
     Fairfax
    0.14
    opies
    0.14
    imity
    0.14
    aylor
    0.14
     Duffy
    0.14
    θα
    0.13
    antage
    0.13
    Act Density 0.232%

    No Known Activations