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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases related to having, owning, or seizing something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating possession or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Shock
    -0.61
    strength
    -0.59
    abuse
    -0.58
     ETH
    -0.58
    Los
    -0.57
    DF
    -0.56
     disbelief
    -0.56
    asive
    -0.55
     srfAttach
    -0.54
    ateful
    -0.54
    POSITIVE LOGITS
     done
    1.23
     accomplished
    1.12
     wrought
    1.11
     achieved
    1.04
     been
    1.03
     learnt
    1.01
    done
    1.01
     gotten
    0.95
     undergone
    0.94
     taught
    0.92
    Act Density 0.059%

    No Known Activations