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

    Neuronpedia

    INDEX
    Explanations

    actions involving physical movement or struggle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fft
    -0.15
    ÑĪев
    -0.14
    olvers
    -0.14
    bond
    -0.14
    ullets
    -0.14
    fern
    -0.14
     Knot
    -0.13
    edes
    -0.13
     throat
    -0.13
     Slee
    -0.13
    POSITIVE LOGITS
     balance
    0.41
     Balance
    0.40
     stability
    0.35
     instability
    0.34
    balance
    0.34
    Balance
    0.34
     Stability
    0.32
     unstable
    0.32
     stead
    0.28
     balancing
    0.28
    Act Density 0.155%

    No Known Activations