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

    Neuronpedia

    INDEX
    Explanations

    terms related to motorcycle helmets and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bund
    -0.17
     Sofa
    -0.16
     Couch
    -0.15
    undi
    -0.15
     Cancer
    -0.14
    awy
    -0.14
    vig
    -0.14
    bane
    -0.14
    sass
    -0.14
    777
    -0.14
    POSITIVE LOGITS
     helmet
    0.38
     helmets
    0.37
    hel
    0.32
     Helmet
    0.32
    helm
    0.30
    Helmet
    0.30
     Helm
    0.29
     chin
    0.27
     MIPS
    0.27
     vis
    0.24
    Act Density 0.028%

    No Known Activations