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

    Neuronpedia

    INDEX
    Explanations

    elements related to protective features and functionality in objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ì
    -0.14
    lob
    -0.14
    داÙĨ
    -0.14
     Glover
    -0.14
     Serg
    -0.13
     Harding
    -0.13
    amps
    -0.13
    ugi
    -0.13
    OTT
    -0.13
     bast
    -0.13
    POSITIVE LOGITS
     drafts
    0.18
     prevents
    0.17
     protection
    0.15
    aldi
    0.15
     prevent
    0.15
    prevent
    0.15
    .seed
    0.14
     preventing
    0.14
     Hairst
    0.14
    Draft
    0.14
    Act Density 0.087%

    No Known Activations