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

    Neuronpedia

    INDEX
    Explanations

    references to the word "who."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uron
    -0.64
    sety
    -0.55
    avance
    -0.55
    ある
    -0.54
    前の
    -0.54
    uet
    -0.54
    あれば
    -0.54
    ὴν
    -0.52
    iertos
    -0.52
    一つの
    -0.51
    POSITIVE LOGITS
     who
    4.29
    who
    3.79
     Who
    3.50
    Who
    3.42
     whom
    3.08
     quien
    2.87
    whom
    2.81
    WHO
    2.74
     WHO
    2.72
     quién
    2.52
    Act Density 0.082%

    No Known Activations