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

    Neuronpedia

    INDEX
    Explanations

    pronouns and verbs related to seeking information or understanding

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "We" or its variations, indicating a focus on collective actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    forms
    -0.68
     Haku
    -0.61
     guiActiveUnfocused
    -0.59
     decoration
    -0.58
    ãĤ³
    -0.57
    Application
    -0.56
     fluids
    -0.56
     flows
    -0.56
    MY
    -0.56
    andon
    -0.56
    POSITIVE LOGITS
    akening
    1.08
    athered
    1.05
    ibo
    1.01
    've
    0.99
    asel
    0.99
    blogs
    0.98
     wondered
    0.97
    ighed
    0.97
    igh
    0.95
    'll
    0.94
    Act Density 0.188%

    No Known Activations