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

    Neuronpedia

    INDEX
    Explanations

    expressions of disbelief or strong reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WritableDatabase
    -0.54
    ,
    -0.53
     Asimismo
    -0.48
    ШЕ
    -0.46
     которое
    -0.45
     brevi
    -0.44
     locally
    -0.43
    routeProvider
    -0.42
    ESCO
    -0.42
     iliy
    -0.41
    POSITIVE LOGITS
     متعلقه
    0.79
    "])
    0.76
     }</
    0.71
    "],
    0.71
    ")){
    0.69
    原始内容存档于
    0.69
    ")]
    0.69
    ()]
    0.69
    ItemBackground
    0.68
     this
    0.67
    Act Density 0.162%

    No Known Activations