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

    Neuronpedia

    INDEX
    Explanations

    aspects related to dining experiences and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    msgid
    -0.31
    MessageState
    -0.28
     cour
    -0.27
     REP
    -0.27
    几次
    -0.27
    InputBorder
    -0.27
     conf
    -0.27
     Repe
    -0.27
     selection
    -0.26
     alumínio
    -0.26
    POSITIVE LOGITS
    两个人
    0.92
    二人
    0.89
    三人
    0.88
    一人
    0.87
     berdua
    0.86
    兩人
    0.85
     solo
    0.81
    四人
    0.79
    两人
    0.75
     duos
    0.73
    Act Density 0.251%

    No Known Activations