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

    Neuronpedia

    INDEX
    Explanations

    policy-related actions and instruments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    in
    -0.15
    -
    -0.15
    enna
    -0.15
    [
    -0.15
    eters
    -0.14
    º
    -0.14
     Yuan
    -0.14
    c
    -0.14
     st
    -0.13
    ET
    -0.13
    POSITIVE LOGITS
    lessly
    0.20
    isque
    0.18
    (Paint
    0.17
    SizeMode
    0.17
    .firebaseapp
    0.17
    weeted
    0.16
    çĦ¡ãģĹãģ
    0.16
    itele
    0.15
    ogui
    0.15
    âĻª↵↵
    0.15
    Act Density 0.588%

    No Known Activations