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

    Neuronpedia

    INDEX
    Explanations

    words related to stability or a lack of emotion

    oai_token-act-pair · gpt-3.5-turbo

    references to balance or balancing concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    printf
    -0.82
    rawl
    -0.82
     deposition
    -0.73
    thood
    -0.71
    ribe
    -0.71
    print
    -0.69
     Expand
    -0.66
    iblings
    -0.65
    XP
    -0.65
     Profession
    -0.64
    POSITIVE LOGITS
     bal
    4.01
    Bal
    2.17
     Bal
    1.90
    bal
    1.66
     BAL
    1.11
     ballet
    1.07
     balancing
    1.00
     sto
    1.00
     sab
    0.99
     peac
    0.96
    Act Density 0.029%

    No Known Activations