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

    Neuronpedia

    INDEX
    Explanations

    specific names and titles of people or literary works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spy
    -0.15
     dish
    -0.14
    kip
    -0.14
     elite
    -0.14
     Assignment
    -0.14
    Spy
    -0.14
    ucer
    -0.14
    仪
    -0.14
    hil
    -0.14
     dep
    -0.14
    POSITIVE LOGITS
     rac
    0.23
     Rac
    0.20
    rac
    0.19
     Quad
    0.17
    opard
    0.17
     scaff
    0.17
     Editor
    0.16
    aut
    0.16
     ese
    0.16
    editor
    0.16
    Act Density 0.015%

    No Known Activations