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

    Neuronpedia

    INDEX
    Explanations

    terms related to safety features and crash test evaluations of vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    747
    -0.16
     Dil
    -0.15
     Dad
    -0.15
    cipher
    -0.14
     Finger
    -0.14
     Kaplan
    -0.14
    AZY
    -0.14
     Cipher
    -0.13
    леÑĢ
    -0.13
    æĻ´
    -0.13
    POSITIVE LOGITS
     crash
    0.36
     Crash
    0.31
     frontal
    0.28
     occup
    0.25
     crashes
    0.23
     II
    0.22
     collision
    0.22
     protection
    0.22
     tests
    0.22
     safety
    0.21
    Act Density 0.026%

    No Known Activations