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

    Neuronpedia

    INDEX
    Explanations

    mentions of automotive safety features and their effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leneck
    -0.15
    .gdx
    -0.15
    .fm
    -0.15
    (___
    -0.14
    ì£
    -0.14
    anje
    -0.14
    lene
    -0.14
    ednou
    -0.14
    목
    -0.14
     Ùģار
    -0.14
    POSITIVE LOGITS
     safety
    0.20
     features
    0.20
     feature
    0.18
     Safety
    0.17
     automatic
    0.17
    åĥį
    0.16
     signal
    0.16
     advanced
    0.16
     hon
    0.15
     rear
    0.15
    Act Density 0.018%

    No Known Activations