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

    Neuronpedia

    INDEX
    Explanations

    references to prestigious events or noteworthy achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dw
    -0.15
    wald
    -0.14
     Narc
    -0.14
     Dwarf
    -0.14
     Hann
    -0.13
    ssl
    -0.13
     IA
    -0.13
    代çIJĨ
    -0.13
     ccp
    -0.13
    ÑĢал
    -0.13
    POSITIVE LOGITS
     Arthur
    0.25
     Ashe
    0.23
     Fl
    0.21
    Arthur
    0.20
     Venus
    0.19
     US
    0.18
     Grand
    0.18
     Ary
    0.18
     Slam
    0.18
     Stephens
    0.18
    Act Density 0.005%

    No Known Activations