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

    Neuronpedia

    INDEX
    Explanations

    business-related terms and actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iannopoulos
    -0.77
    pmwiki
    -0.77
     Recall
    -0.72
    %:
    -0.70
     è£ıè
    -0.70
     Reasons
    -0.69
    TO
    -0.68
    etheless
    -0.67
     Amid
    -0.66
     âĹ
    -0.66
    POSITIVE LOGITS
     gonna
    1.36
     somebody
    1.17
     going
    1.11
     kind
    1.10
     saying
    1.10
     really
    1.05
     sort
    1.03
     doing
    1.01
     basically
    0.98
     trying
    0.97
    Act Density 0.325%

    No Known Activations