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

    Neuronpedia

    INDEX
    Explanations

    words related to influence, impact, or change

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of shaping or influencing various aspects of society or personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unts
    -0.72
     Mub
    -0.65
    ciation
    -0.64
    ysis
    -0.60
    employed
    -0.59
     scrape
    -0.58
     istg
    -0.58
    blers
    -0.57
     typew
    -0.57
    itars
    -0.56
    POSITIVE LOGITS
     perceptions
    0.91
    glers
    0.87
     shaping
    0.78
     destiny
    0.75
    ãĥį
    0.71
     attitudes
    0.71
     traject
    0.70
    eering
    0.69
     into
    0.69
    insula
    0.69
    Act Density 0.034%

    No Known Activations