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

    Neuronpedia

    INDEX
    Explanations

    words related to legal and official actions, such as confirmation, condemnation, explanation, indictment, pronouncement, reimbursement, attendance, happening, appointment, understanding, disappointment, inhabitation, oppression, representation, alteration, retirement, invitation, and sentencing

    oai_token-act-pair · gpt-3.5-turbo

    words associated with legal and political processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     crane
    -0.64
    utenberg
    -0.64
     brow
    -0.63
     foremost
    -0.62
     abundantly
    -0.61
     Hurricanes
    -0.60
    ItemTracker
    -0.60
     KR
    -0.58
     Mehran
    -0.57
    0200
    -0.57
    POSITIVE LOGITS
    ments
    1.88
    ings
    1.63
    ations
    1.50
    able
    1.47
    ances
    1.42
    ables
    1.42
    ement
    1.38
    ational
    1.37
    ability
    1.32
    ibles
    1.32
    Act Density 0.284%

    No Known Activations