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

    Neuronpedia

    INDEX
    Explanations

    programming structures and elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Miri
    -0.51
     Knud
    -0.50
     roti
    -0.50
     Mako
    -0.48
     Lyra
    -0.47
     hei
    -0.47
     Krak
    -0.46
     Favre
    -0.46
     Upp
    -0.46
     Cef
    -0.45
    POSITIVE LOGITS
     Gerechtigkeit
    0.66
     sereia
    0.60
     Schaefer
    0.59
     Cárdenas
    0.57
     Clements
    0.57
     Naciones
    0.57
     maternidade
    0.57
     Sünde
    0.56
     Pritchard
    0.56
     Hanson
    0.56
    Act Density 1.201%

    No Known Activations