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

    Neuronpedia

    INDEX
    Explanations

    pronouns and verbs indicating actions or states

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "they" and closely related personal pronouns that indicate agency or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     delaying
    -0.70
     preferring
    -0.70
    holding
    -0.60
     occurring
    -0.60
    ãĥ´
    -0.60
    pired
    -0.60
    PDATE
    -0.59
    ãĤ¬
    -0.58
    ãĤ¹ãĥĪ
    -0.58
     Prediction
    -0.58
    POSITIVE LOGITS
     reaches
    0.95
     reach
    0.93
     finally
    0.82
     realise
    0.78
     reached
    0.77
     finishes
    0.76
    yrinth
    0.76
     expires
    0.76
     realizes
    0.76
     realize
    0.76
    Act Density 0.116%

    No Known Activations