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

    Neuronpedia

    INDEX
    Explanations

    sentences describing a state or process

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "being."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PsyNetMessage
    -0.74
     Dag
    -0.68
    inav
    -0.66
     Beginning
    -0.63
    eva
    -0.61
     Surv
    -0.61
     liking
    -0.61
    å£
    -0.61
    luck
    -0.61
     Lag
    -0.60
    POSITIVE LOGITS
     able
    1.17
     chased
    0.96
     pushed
    0.91
     eaten
    0.91
     replaced
    0.90
     flung
    0.89
     transported
    0.89
     hailed
    0.89
     ridden
    0.88
    held
    0.88
    Act Density 0.081%

    No Known Activations