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

    Neuronpedia

    INDEX
    Explanations

    references to singular and plural forms of the word "one."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    expandindo
    -0.82
     CreateTagHelper
    -0.81
     pleaſure
    -0.79
    Portale
    -0.78
     дописавши
    -0.75
     houſe
    -0.74
    IntoConstraints
    -0.74
     myſelf
    -0.73
     ProtoMessage
    -0.72
     poffible
    -0.72
    POSITIVE LOGITS
     celles
    0.68
     aqueles
    0.62
     quelli
    0.59
     ceux
    0.59
     cuales
    0.56
     ones
    0.54
    osen
    0.53
     quello
    0.51
     who
    0.51
     Ceux
    0.51
    Act Density 0.243%

    No Known Activations