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

    Neuronpedia

    INDEX
    Explanations

    questions about processes, methodologies, and how things work

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iku
    -0.52
     Stein
    -0.50
    SPJ
    -0.48
    zenberg
    -0.48
    지
    -0.48
     <
    -0.48
     [
    -0.47
    のも
    -0.47
    ünster
    -0.45
    DB
    -0.45
    POSITIVE LOGITS
    איך
    1.09
     how
    1.09
     איך
    1.07
     कैसे
    1.06
     Hvordan
    1.00
     hogyan
    1.00
    Kako
    0.99
     miten
    0.98
     Nasıl
    0.95
    cómo
    0.94
    Act Density 0.120%

    No Known Activations