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

    Neuronpedia

    INDEX
    Explanations

    references to the reader's actions and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pie
    -0.19
    ALLE
    -0.15
     pie
    -0.15
    artin
    -0.14
     qu
    -0.14
    URT
    -0.14
     itself
    -0.14
    arc
    -0.13
     sophistication
    -0.13
     anonymous
    -0.13
    POSITIVE LOGITS
    emann
    0.18
    nger
    0.16
    offer
    0.16
    avier
    0.16
    GI
    0.15
    uego
    0.15
     offering
    0.15
     ofrece
    0.15
    gorith
    0.15
    ioni
    0.15
    Act Density 0.330%

    No Known Activations