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

    Neuronpedia

    INDEX
    Explanations

    phrases related to dipping or immersing items in substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    smithy
    -0.60
     tartalomajánló
    -0.54
     '\\;'
    -0.54
     \]
    -0.54
    xFFFFFF
    -0.53
    pidou
    -0.52
    ushchev
    -0.52
    MessageOf
    -0.51
     >=",
    -0.51
     express
    -0.51
    POSITIVE LOGITS
     dipped
    1.11
     immersion
    1.11
     dipping
    1.08
     Immersion
    1.05
     immersed
    1.04
     mergul
    1.02
     dunk
    1.00
     submer
    0.99
     dips
    0.98
    Dip
    0.97
    Act Density 0.133%

    No Known Activations