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

    Neuronpedia

    INDEX
    Explanations

    words related to stabilization or making things stable

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to stability and stabilization in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    boro
    -0.74
    lege
    -0.72
     Pepsi
    -0.71
    Letter
    -0.71
    mine
    -0.70
    ebook
    -0.70
    reply
    -0.69
     Letter
    -0.66
    rets
    -0.66
    arious
    -0.66
    POSITIVE LOGITS
     stabil
    3.70
     stabilization
    3.11
     stabilized
    2.98
     stabilize
    2.97
     stability
    1.78
     destabil
    1.73
    abil
    1.56
     Stability
    1.44
     stable
    1.41
     calming
    1.28
    Act Density 0.013%

    No Known Activations