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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to directional and positional terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.53
    Aholisi
    -0.48
     giường
    -0.45
    ichteten
    -0.45
    ]){
    -0.44
     Codes
    -0.41
    ETHER
    -0.41
     North
    -0.41
     Lad
    -0.41
     
    -0.41
    POSITIVE LOGITS
    WebVitals
    0.85
     []:
    0.82
     оригіналу
    0.77
     contextLoads
    0.77
    enderror
    0.76
    存于互联网档案馆
    0.76
    RunAsync
    0.76
    lgari
    0.76
    IndentedString
    0.75
    TargetException
    0.74
    Act Density 0.069%

    No Known Activations