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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the term "Whit" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iros
    -0.19
    elmet
    -0.18
    hood
    -0.18
    hole
    -0.17
    hydr
    -0.16
    Æ°Æ¡ng
    -0.15
    atinum
    -0.15
    olini
    -0.15
    uments
    -0.15
     bride
    -0.15
    POSITIVE LOGITS
    son
    0.17
    ting
    0.17
     champs
    0.15
    nell
    0.15
    aker
    0.15
    kop
    0.15
    âĨĵ
    0.15
    æĺ
    0.15
    tp
    0.14
    plash
    0.14
    Act Density 0.010%

    No Known Activations