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

    Neuronpedia

    INDEX
    Explanations

    questions and conditional phrases related to methods or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eſt
    -0.69
     entanto
    -0.58
     juf
    -0.57
    دانشنامهٔ
    -0.57
    seamnă
    -0.57
     juſ
    -0.57
     châssis
    -0.57
     pleaf
    -0.56
     Manns
    -0.56
    zner
    -0.56
    POSITIVE LOGITS
     jak
    0.88
     що
    0.80
     что
    0.76
     quanto
    0.72
     як
    0.71
     jaki
    0.70
     cómo
    0.70
     как
    0.69
    Quanto
    0.69
     jakie
    0.69
    Act Density 0.068%

    No Known Activations