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

    Neuronpedia

    INDEX
    Explanations

    questions about personal preferences and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hel
    -0.18
    oste
    -0.17
    ple
    -0.14
     hel
    -0.14
    isphere
    -0.14
    inda
    -0.14
    gren
    -0.14
     Barth
    -0.14
    aks
    -0.14
     ple
    -0.13
    POSITIVE LOGITS
     favourite
    0.22
     favorite
    0.22
    favorite
    0.20
     Describe
    0.19
    Describe
    0.19
    Favorite
    0.17
     Favorite
    0.17
     describe
    0.17
    describe
    0.15
    otto
    0.14
    Act Density 0.039%

    No Known Activations