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

    Neuronpedia

    INDEX
    Explanations

    terms related to stability and instability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yb
    -0.18
    eren
    -0.17
    ylül
    -0.17
    \Migration
    -0.17
    ivity
    -0.16
    el
    -0.16
    onne
    -0.16
    esis
    -0.16
    etre
    -0.16
    escape
    -0.15
    POSITIVE LOGITS
    coins
    0.22
    mate
    0.20
    coin
    0.19
     footing
    0.19
    mates
    0.19
     unstable
    0.19
    ilty
    0.18
    /un
    0.17
     stability
    0.17
    ment
    0.17
    Act Density 0.031%

    No Known Activations