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

    Neuronpedia

    INDEX
    Explanations

    the word "meant" and its variations, indicating the significance or implications of statements in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſever
    -1.16
     juſ
    -1.12
     fubject
    -1.08
     ―――――
    -1.07
     tranſ
    -1.04
     raiſ
    -1.01
     ſeveral
    -1.00
     ſta
    -1.00
     uſed
    -0.98
     ſub
    -0.96
    POSITIVE LOGITS
     meant
    1.24
     meaning
    1.01
    meant
    0.96
    meaning
    0.85
     Meaning
    0.80
    Meaning
    0.78
     Mean
    0.78
     MEAN
    0.70
     mean
    0.69
     meanings
    0.68
    Act Density 0.120%

    No Known Activations