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

    Neuronpedia

    INDEX
    Explanations

    adjectives or verbs indicating value judgments

    oai_token-act-pair · gpt-3.5-turbo

    the verb "is" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.71
     ABE
    -0.71
    ONSORED
    -0.69
    ¥ŀ
    -0.66
    ADS
    -0.63
     Buff
    -0.63
    ORK
    -0.61
     Styles
    -0.59
     banner
    -0.59
    Ĥª
    -0.58
    POSITIVE LOGITS
    estate
    0.90
    sel
    0.90
    quel
    0.88
    ciation
    0.88
    cience
    0.88
    pect
    0.87
    earch
    0.87
    sei
    0.87
    quer
    0.87
    ceed
    0.86
    Act Density 0.051%

    No Known Activations