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

    Neuronpedia

    INDEX
    Explanations

    references to power dynamics and influence in social or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ê·¹
    -0.18
    acin
    -0.15
    isan
    -0.14
    lassen
    -0.14
     Dich
    -0.14
    ük
    -0.14
     Bits
    -0.14
    arity
    -0.14
    uard
    -0.13
     ConfigurationManager
    -0.13
    POSITIVE LOGITS
     cl
    0.48
     influence
    0.43
     power
    0.35
     sway
    0.34
     weight
    0.34
     authority
    0.34
     Influence
    0.32
     standing
    0.32
     muscle
    0.32
     cach
    0.30
    Act Density 0.251%

    No Known Activations