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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "who."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mente
    -0.16
    idan
    -0.16
    utor
    -0.16
    ned
    -0.16
    lix
    -0.15
    idious
    -0.15
    uries
    -0.15
    ly
    -0.15
    rad
    -0.15
    nya
    -0.14
    POSITIVE LOGITS
    oping
    0.34
    upon
    0.28
    oped
    0.23
    soever
    0.23
    've
    0.23
    'd
    0.21
    ’ve
    0.21
    ever
    0.20
    ’d
    0.20
     despite
    0.20
    Act Density 0.141%

    No Known Activations