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

    Neuronpedia

    INDEX
    Explanations

    verbs related to the action of possessing or experiencing something

    oai_token-act-pair · gpt-3.5-turbo

    repetitive use of the phrase "to have."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    catentry
    -0.63
     fireball
    -0.62
    etter
    -0.60
     anticipating
    -0.58
     Echo
    -0.57
    etting
    -0.56
    ocol
    -0.56
     backdrop
    -0.55
     wounding
    -0.55
     hostage
    -0.55
    POSITIVE LOGITS
     been
    1.06
     gotten
    1.02
    been
    0.89
     undergone
    0.87
     taken
    0.85
     eaten
    0.82
     seen
    0.82
    gotten
    0.81
     done
    0.80
     Been
    0.80
    Act Density 0.144%

    No Known Activations