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

    Neuronpedia

    INDEX
    Explanations

    instances of the pronoun "you"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     might
    -0.53
     måske
    -0.53
     entweder
    -0.53
     either
    -0.51
     enten
    -0.50
     kanskje
    -0.49
    יוחד
    -0.48
     kanske
    -0.48
    either
    -0.46
     Either
    -0.45
    POSITIVE LOGITS
     ever
    1.00
     saites
    0.92
     hadn
    0.90
     anything
    0.88
     typelib
    0.84
    anything
    0.84
     Roskov
    0.83
     EVER
    0.83
     resourceCulture
    0.81
    AlterField
    0.78
    Act Density 0.118%

    No Known Activations