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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate specific conditions or contexts relating to analysis or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Inter
    -0.45
     Virgin
    -0.44
     
    -0.43
    Write
    -0.43
     or
    -0.42
     La
    -0.42
    brun
    -0.41
    wal
    -0.41
     sementara
    -0.41
     longa
    -0.40
    POSITIVE LOGITS
     nahilalakip
    1.35
    httphttps
    1.25
     snippetHide
    1.14
    دانشنامهٔ
    1.12
     InputDecoration
    1.06
     للاسماء
    1.06
    KommentareTeilen
    1.06
     propOrder
    1.05
     Мексичка
    1.04
     GenerationType
    1.03
    Act Density 0.112%

    No Known Activations