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

    Neuronpedia

    INDEX
    Explanations

    references to archaeological discoveries and findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Locked
    -0.15
     Holocaust
    -0.14
     Cruiser
    -0.14
     USED
    -0.13
     Damen
    -0.13
    abwe
    -0.13
     بÙĪر
    -0.13
    aight
    -0.13
     ÙħØ«
    -0.13
    uvo
    -0.13
    POSITIVE LOGITS
     Circ
    0.21
     Che
    0.21
     Ing
    0.19
     Caucas
    0.19
     Caucasian
    0.18
    ynes
    0.16
    nier
    0.16
    imli
    0.16
     Gro
    0.16
    Mountain
    0.15
    Act Density 0.020%

    No Known Activations