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

    Neuronpedia

    INDEX
    Explanations

    references to senior-level positions and titles in organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gi
    -0.17
    efeller
    -0.16
    pert
    -0.15
    ãĥ³ãĥĸ
    -0.15
    ting
    -0.15
    ionario
    -0.14
    γο
    -0.14
    enders
    -0.14
    away
    -0.14
    go
    -0.14
    POSITIVE LOGITS
    ity
    0.41
    -most
    0.36
     citizens
    0.25
    -level
    0.25
     citizen
    0.23
    itis
    0.23
     Citizens
    0.22
    most
    0.21
    ities
    0.21
     level
    0.19
    Act Density 0.019%

    No Known Activations