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

    Neuronpedia

    INDEX
    Explanations

    discussions about dependency and causation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ersion
    -0.17
    olas
    -0.17
    ustin
    -0.17
    axies
    -0.16
    agal
    -0.16
    ondon
    -0.15
    AVIS
    -0.15
    weed
    -0.15
    emann
    -0.14
    ãģĤãĤĬãģĮãģ¨ãģĨ
    -0.14
    POSITIVE LOGITS
    uf
    0.18
    Portal
    0.15
    -Smith
    0.14
    å®Ī
    0.14
     Sai
    0.14
     saf
    0.14
    -metadata
    0.14
     CLI
    0.13
     Definition
    0.13
    uet
    0.13
    Act Density 0.420%

    No Known Activations