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

    Neuronpedia

    INDEX
    Explanations

    discussions around public perception and recognition of individuals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urvey
    -0.18
    itsu
    -0.15
    Pitch
    -0.15
     Pew
    -0.15
    ilden
    -0.15
    ilver
    -0.15
    ustom
    -0.14
    imet
    -0.14
    owitz
    -0.14
    noop
    -0.14
    POSITIVE LOGITS
     him
    0.30
    ä»ĸçļĦ
    0.22
     ihn
    0.22
     그를
    0.21
     his
    0.21
     ihm
    0.20
     onun
    0.19
     lui
    0.19
    his
    0.18
     عÙĨÙĩ
    0.17
    Act Density 0.449%

    No Known Activations