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

    Neuronpedia

    INDEX
    Explanations

    prepositions typically used to indicate direction or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.10
     raiſ
    -1.04
     houſe
    -1.04
     ſever
    -1.04
     Houſe
    -1.02
     Majefty
    -1.02
     faſt
    -1.00
     Jefus
    -0.95
     purpoſe
    -0.94
     ſta
    -0.93
    POSITIVE LOGITS
     به
    1.49
    به
    1.10
     på
    0.99
     auf
    0.91
     Auf
    0.90
     به‌
    0.89
     På
    0.79
    }]{
    0.77
     بح
    0.76
     از
    0.74
    Act Density 0.022%

    No Known Activations