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

    Neuronpedia

    INDEX
    Explanations

    phrases related to authority and decision-making powers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agar
    -0.19
    ALIGN
    -0.16
    zv
    -0.15
    TextNode
    -0.15
    ÑĢÑĥÑĩ
    -0.15
    лиÑĩ
    -0.14
    AGR
    -0.14
    wake
    -0.14
    rimp
    -0.14
    xfa
    -0.14
    POSITIVE LOGITS
     authority
    0.20
     freely
    0.19
     cross
    0.16
    acb
    0.15
    azon
    0.15
     decisions
    0.15
    authority
    0.15
     cause
    0.15
     unlimited
    0.15
     carte
    0.15
    Act Density 0.090%

    No Known Activations