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

    Neuronpedia

    INDEX
    Explanations

    instructions or guidelines related to a process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     verfolgt
    -0.57
    ressible
    -0.55
     Xunit
    -0.54
    secuted
    -0.53
    ğine
    -0.52
     orgull
    -0.51
     pursued
    -0.51
     للمعارف
    -0.50
     Utf
    -0.49
    niosek
    -0.49
    POSITIVE LOGITS
     familiarize
    1.11
     acc
    0.99
     familiar
    0.98
     learning
    0.96
     adjustment
    0.95
     settling
    0.91
     Familiar
    0.90
     acost
    0.89
    familiar
    0.88
     adjusting
    0.87
    Act Density 0.273%

    No Known Activations