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

    Neuronpedia

    INDEX
    Explanations

    questions related to personal and moral dilemmas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ighbor
    -0.17
    apiro
    -0.17
    scenario
    -0.17
    olis
    -0.16
     Scenario
    -0.15
    Scenario
    -0.14
    ordion
    -0.14
     Plantae
    -0.14
    bedo
    -0.14
    zell
    -0.14
    POSITIVE LOGITS
    iates
    0.16
     desert
    0.15
     stability
    0.15
     Blue
    0.15
     Stability
    0.15
     preced
    0.14
     Ãľst
    0.14
    endar
    0.13
     Car
    0.13
    inactive
    0.13
    Act Density 0.111%

    No Known Activations