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

    Neuronpedia

    INDEX
    Explanations

    specific characters or symbols that indicate emotional or descriptive expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ंदीखरीदारी
    -0.58
    Autoritní
    -0.54
     CURIAM
    -0.51
    原标题
    -0.47
     dignité
    -0.46
    
    -0.46
    consulté
    -0.45
    windowFixed
    -0.44
     PeEnEo
    -0.44
    berdayakan
    -0.43
    POSITIVE LOGITS
     Вікі
    0.47
     Albert
    0.38
    berger
    0.38
    ECAUSE
    0.37
    ector
    0.37
    QUIR
    0.37
    ROL
    0.37
    BaseType
    0.37
     Worthington
    0.37
     Kirsten
    0.36
    Act Density 0.057%

    No Known Activations