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

    Neuronpedia

    INDEX
    Explanations

    references to announcements or mentions of names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    innen
    -0.15
    iggins
    -0.15
    ãģ¾ãģ¾
    -0.14
    ÙĨدÙĬØ©
    -0.14
    o
    -0.14
    vez
    -0.14
    -0.14
    ãĥ³ãĤ°
    -0.14
    eydi
    -0.13
    cloak
    -0.13
    POSITIVE LOGITS
    ihilation
    0.28
    ouncements
    0.25
    ivers
    0.23
     Arbor
    0.23
    .SuppressLint
    0.23
    ouncing
    0.21
    ounced
    0.20
    ounces
    0.19
    exe
    0.19
    iversary
    0.19
    Act Density 0.016%

    No Known Activations