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

    Neuronpedia

    INDEX
    Explanations

    references to safety features and enhancements in vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plements
    -0.16
    lez
    -0.15
    malink
    -0.15
     Batter
    -0.15
    dera
    -0.14
    .Void
    -0.14
     ÙĨØ®
    -0.14
    ëł
    -0.14
    ören
    -0.14
    .until
    -0.14
    POSITIVE LOGITS
    illo
    0.15
    alar
    0.15
     Rio
    0.14
    lie
    0.14
     Mell
    0.13
     su
    0.13
    fx
    0.13
     Coca
    0.13
    ystone
    0.13
    ivity
    0.13
    Act Density 0.095%

    No Known Activations