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

    Neuronpedia

    INDEX
    Explanations

    words related to sudden increases or high levels of something, such as "soared" or "soaring."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to significant increases or rises in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.81
    put
    -0.72
    Wr
    -0.71
    OH
    -0.71
    essee
    -0.68
     Trials
    -0.68
    ________________________________
    -0.66
    War
    -0.66
    optional
    -0.64
     Territories
    -0.62
    POSITIVE LOGITS
     soaring
    1.08
     soared
    1.07
     soar
    1.00
     plummet
    0.87
    acebook
    0.82
    wcs
    0.81
     skyrocket
    0.79
     plummeted
    0.78
    efully
    0.77
     tremend
    0.76
    Act Density 0.016%

    No Known Activations