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

    Neuronpedia

    INDEX
    Explanations

    the word "wipe" and variations of "flour"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
      
    -0.53
     d
    -0.52
    ,
    -0.51
     El
    -0.51
     for
    -0.49
    ↵
    -0.48
    el
    -0.48
     the
    -0.47
    devtools
    -0.47
     el
    -0.46
    POSITIVE LOGITS
     wipe
    1.67
     wiped
    1.50
     wiping
    1.36
     Wipe
    1.33
    Wipe
    1.33
    wipe
    1.26
     Theſe
    1.20
     wipes
    1.20
     Efq
    1.13
     Monfieur
    1.05
    Act Density 0.070%

    No Known Activations