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

    Neuronpedia

    INDEX
    Explanations

    terms related to interests or beliefs of different groups or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of interests, particularly in a political or social context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aan
    -0.77
    aston
    -0.73
    ãĤ¨ãĥ«
    -0.69
    ergy
    -0.68
    åī
    -0.67
    ework
    -0.67
    BuyableInstoreAndOnline
    -0.66
    á
    -0.65
    anne
    -0.63
    aus
    -0.63
    POSITIVE LOGITS
     interests
    1.01
    reprene
    0.85
     territ
    0.75
    igent
    0.75
    awaru
    0.74
     Groups
    0.73
    afe
    0.72
    edIn
    0.70
     groups
    0.69
     shareholders
    0.69
    Act Density 0.035%

    No Known Activations