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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal actions and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Celt
    -0.16
    igid
    -0.15
    ζα
    -0.14
     Stealth
    -0.14
     cứu
    -0.14
    æķij
    -0.14
     resc
    -0.14
    habi
    -0.13
    IXEL
    -0.13
     turret
    -0.13
    POSITIVE LOGITS
     Simpson
    0.47
     Simpsons
    0.32
     simp
    0.28
     Juice
    0.27
    simp
    0.27
     Nicole
    0.27
     SIM
    0.25
     Kardashian
    0.25
     Goldman
    0.25
    SIM
    0.23
    Act Density 0.001%

    No Known Activations