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

    Neuronpedia

    INDEX
    Explanations

    phrases that refer to specific policies or principles

    oai_token-act-pair · gpt-3.5-turbo

    recurring phrases that indicate policy-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ILCS
    -0.73
     Extras
    -0.69
    */(
    -0.68
    handle
    -0.68
    ãĤ¼ãĤ¦ãĤ¹
    -0.66
    Effects
    -0.66
    acious
    -0.64
    worthy
    -0.63
    bucks
    -0.63
    PI
    -0.62
    POSITIVE LOGITS
     ours
    0.84
     theirs
    0.75
     impunity
    0.75
     neutrality
    0.72
     attrition
    0.71
     promoting
    0.71
     abstinence
    0.69
    interstitial
    0.68
     friendship
    0.68
     nationalism
    0.68
    Act Density 0.176%

    No Known Activations