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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "after"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    migrationBuilder
    -0.92
    itecture
    -0.81
    rillation
    -0.81
    لينكات
    -0.77
    izowane
    -0.74
    MessageTagHelper
    -0.73
     Tun
    -0.72
    XtraGrid
    -0.71
    Égypte
    -0.71
    wrights
    -0.69
    POSITIVE LOGITS
    after
    1.90
     after
    1.88
    After
    1.84
     After
    1.82
     AFTER
    1.70
    AFTER
    1.70
     dopo
    1.56
     Dopo
    1.52
    Dopo
    1.50
     fter
    1.46
    Act Density 0.095%

    No Known Activations