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

    Neuronpedia

    INDEX
    Explanations

    instances of personal identifiers and affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    autres
    -0.58
    
    -0.51
    eadilan
    -0.49
     иной
    -0.48
    地说道
    -0.47
    bigsqcup
    -0.47
    babu
    -0.46
     Paglinawan
    -0.46
    Hrsg
    -0.45
    graphers
    -0.45
    POSITIVE LOGITS
     native
    0.72
     graduate
    0.71
     avid
    0.70
     lifelong
    0.68
     licensed
    0.68
     former
    0.65
     founding
    0.64
     longtime
    0.64
     Vietnam
    0.63
     decorated
    0.61
    Act Density 0.189%

    No Known Activations