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

    Neuronpedia

    INDEX
    Explanations

    phrases and prepositions that indicate causation or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cæsar
    -0.67
     quæ
    -0.66
     ajuns
    -0.64
    ovací
    -0.58
    valdi
    -0.57
    Nuorodos
    -0.56
    berday
    -0.56
    nél
    -0.56
    atoare
    -0.56
    PostMapping
    -0.55
    POSITIVE LOGITS
     wegen
    1.04
     بسبب
    1.04
     karena
    1.03
     vanwege
    1.00
    Because
    0.98
     Aufgrund
    0.98
    Debido
    0.97
     Because
    0.96
     aufgrund
    0.95
    ůli
    0.93
    Act Density 0.144%

    No Known Activations