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

    Neuronpedia

    INDEX
    Explanations

    references to individuals in senior positions or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pert
    -0.16
    away
    -0.15
    tures
    -0.15
    ALER
    -0.15
    gi
    -0.15
    ionario
    -0.15
    γο
    -0.15
    ting
    -0.15
    entials
    -0.15
    ewater
    -0.14
    POSITIVE LOGITS
    ity
    0.40
    -most
    0.33
    -level
    0.24
     citizens
    0.23
    itis
    0.22
     citizen
    0.22
    级
    0.20
     Citizens
    0.20
    most
    0.20
    ities
    0.19
    Act Density 0.020%

    No Known Activations