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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "was" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jefus
    -0.67
     againſt
    -0.64
    ógio
    -0.63
     fince
    -0.62
    μφωνα
    -0.60
     actuelles
    -0.59
     Parli
    -0.59
    Kontrola
    -0.59
     eorum
    -0.59
     becauſe
    -0.57
    POSITIVE LOGITS
     originally
    0.98
     autrefois
    0.98
     originalmente
    0.93
     previously
    0.93
    wolves
    0.79
     able
    0.78
     born
    0.76
     formerly
    0.72
     ayer
    0.72
    previously
    0.71
    Act Density 0.594%

    No Known Activations