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

    Neuronpedia

    INDEX
    Explanations

    references to specific geographic locations and associated infrastructure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     crib
    -0.15
    енко
    -0.15
     ë°ĶìĿ´
    -0.15
    -bin
    -0.14
    aisal
    -0.14
     bull
    -0.14
     Balls
    -0.14
    лаÑĩ
    -0.14
    ÑĢÑĥб
    -0.14
    .son
    -0.14
    POSITIVE LOGITS
     Arg
    0.25
     Astros
    0.25
     Drama
    0.25
     Mess
    0.23
     Kiss
    0.22
    Void
    0.21
     Therm
    0.21
    Mess
    0.21
     Void
    0.21
     Rhodes
    0.20
    Act Density 0.010%

    No Known Activations