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

    Neuronpedia

    INDEX
    Explanations

    references to political controversies and government actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     connexion
    -0.16
    oler
    -0.15
     meld
    -0.15
    901
    -0.15
    usty
    -0.15
     weighting
    -0.15
     renown
    -0.15
     regardless
    -0.14
    uel
    -0.14
    itary
    -0.14
    POSITIVE LOGITS
     till
    0.21
     hog
    0.21
     Till
    0.19
     compuls
    0.18
     suo
    0.18
     derec
    0.18
    alg
    0.17
     Witness
    0.15
     bag
    0.15
    onz
    0.15
    Act Density 0.125%

    No Known Activations