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

    Neuronpedia

    INDEX
    Explanations

    elements and their associated attributes in code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hack
    -0.17
    Hack
    -0.16
     associate
    -0.15
     Neck
    -0.15
     Hack
    -0.14
    gles
    -0.14
    θÏħ
    -0.13
    aci
    -0.13
     sav
    -0.13
    itto
    -0.13
    POSITIVE LOGITS
    (éĩij
    0.15
    igu
    0.15
    elere
    0.15
     interchange
    0.15
    kening
    0.14
    .pref
    0.14
    721
    0.14
    辺
    0.14
     Doch
    0.14
    lagen
    0.14
    Act Density 0.175%

    No Known Activations