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

    Neuronpedia

    INDEX
    Explanations

    indicators of a new beginning or new introductory concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awtextra
    -0.87
    TagMode
    -0.85
    InitStruct
    -0.83
    XmlAccessorType
    -0.81
    basicConfig
    -0.81
    <?
    -0.81
    IsMutable
    -0.80
    ScopeManager
    -0.76
    invokeLater
    -0.76
     للاسماء
    -0.76
    POSITIVE LOGITS
     vandens
    0.46
     urbanas
    0.44
     bouch
    0.42
     urbanos
    0.41
     femeninos
    0.41
     allemande
    0.40
     personne
    0.39
    bitt
    0.39
     denne
    0.38
    .
    0.38
    Act Density 0.109%

    No Known Activations