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

    Neuronpedia

    INDEX
    Explanations

    verbs related to possession or having something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "have" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shock
    -0.63
     shock
    -0.62
    Interested
    -0.61
     Boss
    -0.60
     Warm
    -0.59
    andy
    -0.58
     Apart
    -0.58
     Dud
    -0.57
     âĺħ
    -0.56
    âĹı
    -0.56
    POSITIVE LOGITS
     been
    1.18
    been
    1.04
     gotten
    1.01
     done
    0.99
     seen
    0.97
     achieved
    0.91
     amassed
    0.91
     encountered
    0.90
    hed
    0.90
     undertaken
    0.88
    Act Density 0.125%

    No Known Activations