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

    Neuronpedia

    INDEX
    Explanations

    references to physical appearances or actions that evoke visual imagery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ROTO
    -0.15
     Bakery
    -0.14
    nge
    -0.14
    ervers
    -0.14
    Arena
    -0.13
    OrFail
    -0.13
    iders
    -0.13
    :@"%@",
    -0.13
     Airways
    -0.13
    ucker
    -0.13
    POSITIVE LOGITS
     Indiana
    0.23
     Inspector
    0.21
     Optim
    0.20
     General
    0.20
     President
    0.19
    Indiana
    0.19
     ET
    0.19
     Liber
    0.18
     Captain
    0.18
     Clark
    0.18
    Act Density 0.431%

    No Known Activations