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

    Neuronpedia

    INDEX
    Explanations

    roles and titles associated with government and leadership positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ůr
    -0.17
    achers
    -0.16
    æĺŃ
    -0.15
    çµ
    -0.15
     treasurer
    -0.15
    abin
    -0.14
    ainers
    -0.14
    ì»
    -0.14
    باÙĨ
    -0.14
    ustr
    -0.14
    POSITIVE LOGITS
     acting
    0.42
     Acting
    0.39
     interim
    0.34
    acting
    0.32
     Inter
    0.30
    Act
    0.28
     Deputy
    0.28
     Assistant
    0.26
    Inter
    0.25
     permanent
    0.24
    Act Density 0.141%

    No Known Activations