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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to mining stability and flooding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vil
    -0.16
    anke
    -0.16
    akit
    -0.15
    ELLOW
    -0.15
    sworth
    -0.15
     egret
    -0.15
    éĻ¸
    -0.15
    дом
    -0.14
    ÄIJT
    -0.14
     serm
    -0.14
    POSITIVE LOGITS
     shaft
    0.33
     mine
    0.31
    shaft
    0.28
     workings
    0.27
     drift
    0.26
     tunnel
    0.25
     tunnels
    0.25
     Shaft
    0.25
     miners
    0.24
    sha
    0.23
    Act Density 0.023%

    No Known Activations