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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize absoluteness or totality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.44
     Gro
    -0.44
     o
    -0.42
     embarked
    -0.41
    BufferException
    -0.40
     Chi
    -0.39
     Fab
    -0.39
    <bos>
    -0.39
     v
    -0.39
     Popp
    -0.38
    POSITIVE LOGITS
    Completely
    1.26
     completely
    1.25
     Completely
    1.20
    completely
    1.20
     totally
    1.10
     completamente
    1.09
     complètement
    1.08
    Totally
    1.04
     teljesen
    1.00
    totally
    0.98
    Act Density 0.215%

    No Known Activations