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

    Neuronpedia

    INDEX
    Explanations

    phrases that inquire about types or categories of things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Económica
    -0.43
    原始内容存档于
    -0.40
     gekomen
    -0.39
     panahon
    -0.34
     drep
    -0.34
     Wikiseite
    -0.33
     rojos
    -0.33
     Familienname
    -0.32
     Pública
    -0.31
     correspondiente
    -0.31
    POSITIVE LOGITS
    gelijke
    0.65
     Biôgrafia
    0.64
    gelijk
    0.56
    styleType
    0.55
    enderror
    0.54
    SequentialGroup
    0.53
    ReusableCell
    0.52
    veck
    0.52
    uzzy
    0.50
    SharedDtor
    0.50
    Act Density 0.182%

    No Known Activations