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

    Neuronpedia

    INDEX
    Explanations

    references to episodes and character interactions in a television series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illac
    -0.18
     Bowl
    -0.17
    祥
    -0.16
     Dwarf
    -0.15
    лава
    -0.14
    ä½
    -0.14
    ãĥ«ãĥī
    -0.14
    زب
    -0.14
    pheric
    -0.13
    keit
    -0.13
    POSITIVE LOGITS
     Hope
    0.26
    Hope
    0.22
     Ridge
    0.20
     Reed
    0.19
     Newman
    0.18
     Roman
    0.18
     Flo
    0.18
     Dollar
    0.17
    ollar
    0.17
    hope
    0.16
    Act Density 0.001%

    No Known Activations