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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "wh."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SuppressLint
    -0.60
    MessageTagHelper
    -0.54
    eldo
    -0.51
    PHONY
    -0.49
     verwijzen
    -0.48
    Tecnologia
    -0.48
    دانشنامهٔ
    -0.47
     laid
    -0.47
     Lohn
    -0.47
    DockStyle
    -0.47
    POSITIVE LOGITS
    Whi
    0.60
     ddelweddau
    0.57
    Wh
    0.56
     CreateTagHelper
    0.55
     beginnetje
    0.54
     Whi
    0.49
    wh
    0.49
     saman
    0.48
     Wh
    0.48
     Habe
    0.48
    Act Density 0.177%

    No Known Activations