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

    Neuronpedia

    INDEX
    Explanations

    phrases about possession or ownership

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "have" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shock
    -0.62
     Warm
    -0.57
     shock
    -0.57
     clicks
    -0.56
     Butcher
    -0.56
     DOT
    -0.56
    wait
    -0.55
     Boss
    -0.55
    âĺħ
    -0.54
     Barron
    -0.53
    POSITIVE LOGITS
     been
    1.12
     gotten
    1.00
     seen
    0.98
     done
    0.96
    been
    0.94
     encountered
    0.93
     amassed
    0.89
    hed
    0.89
     undertaken
    0.87
     learnt
    0.87
    Act Density 0.099%

    No Known Activations