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

    Neuronpedia

    INDEX
    Explanations

    references to senior roles or positions within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gi
    -0.17
    away
    -0.16
    ting
    -0.15
    pane
    -0.15
    tures
    -0.15
    efeller
    -0.15
    ionario
    -0.15
    γο
    -0.15
    aways
    -0.14
    entials
    -0.14
    POSITIVE LOGITS
    ity
    0.40
    -most
    0.36
    -level
    0.24
     citizens
    0.24
    itis
    0.23
     citizen
    0.23
    most
    0.21
    ities
    0.21
     Citizens
    0.21
     vice
    0.20
    Act Density 0.019%

    No Known Activations