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

    Neuronpedia

    INDEX
    Explanations

    references to familial relationships and personal life events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Faz
    -0.40
    lijah
    -0.39
     defin
    -0.37
     Setting
    -0.36
    initializeApp
    -0.36
     prat
    -0.36
     lof
    -0.35
     ans
    -0.35
    bledon
    -0.34
     reta
    -0.34
    POSITIVE LOGITS
     suaminya
    0.61
     caminhada
    0.54
     istrinya
    0.54
     Vernunft
    0.54
    IsMutable
    0.52
    InitVars
    0.51
     cárcel
    0.51
    ArrowToggle
    0.51
    RTEX
    0.51
     święta
    0.51
    Act Density 1.020%

    No Known Activations