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

    Neuronpedia

    INDEX
    Explanations

    references to official positions and titles in organizational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sao
    -0.15
    arya
    -0.15
    iant
    -0.15
    ıng
    -0.15
     cree
    -0.15
     Cory
    -0.14
     Cree
    -0.14
    ï¸
    -0.14
     Mara
    -0.14
     Roths
    -0.14
    POSITIVE LOGITS
     Innoc
    0.24
     Fest
    0.23
     Benson
    0.23
     Collins
    0.21
     Gift
    0.21
     Ones
    0.21
     Prec
    0.20
    ackson
    0.20
     Mesh
    0.19
     Kennedy
    0.19
    Act Density 0.058%

    No Known Activations