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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bow
    -0.53
    berapa
    -0.51
     mấy
    -0.49
     Hæ
    -0.49
    interp
    -0.49
     Bow
    -0.48
    dAtA
    -0.46
    Ữ
    -0.45
    HomeAsUpEnabled
    -0.45
    Bow
    -0.45
    POSITIVE LOGITS
     betweenstory
    0.60
    istorante
    0.52
    utenant
    0.49
    MessageTagHelper
    0.46
    InputBorder
    0.44
     !...
    0.44
     
    0.43
    TokenNameRPAREN
    0.43
     íntimo
    0.43
    transQ
    0.42
    Act Density 2.371%

    No Known Activations