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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating distance or separation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lein
    -0.17
    à¸Ĺาà¸ĩ
    -0.15
    íĥģ
    -0.15
    irim
    -0.15
    Äįek
    -0.14
    899
    -0.14
    jem
    -0.13
    azzi
    -0.13
     IonicModule
    -0.13
    Ïĥη
    -0.13
    POSITIVE LOGITS
     Tet
    0.15
     Yen
    0.15
    lobal
    0.15
    erosis
    0.15
     yet
    0.14
    _Zero
    0.14
    é³
    0.14
    vou
    0.13
    loating
    0.13
    Ïģοι
    0.13
    Act Density 0.029%

    No Known Activations