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

    Neuronpedia

    INDEX
    Explanations

    words related to the process of making something conform to a specific set of rules or standards

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the process of normalization and institutional changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tyard
    -0.79
    agher
    -0.79
    adem
    -0.72
    REL
    -0.71
    stead
    -0.69
    thur
    -0.69
    avering
    -0.68
    bang
    -0.66
    VID
    -0.66
    ben
    -0.66
    POSITIVE LOGITS
     tendencies
    0.82
    ALLY
    0.70
     processes
    0.68
    ATION
    0.67
    âĶĢâĶĢâĶĢâĶĢ
    0.65
     mechanisms
    0.63
     kinderg
    0.62
    SHIP
    0.62
     Judaism
    0.61
    ATIONS
    0.60
    Act Density 0.147%

    No Known Activations