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

    Neuronpedia

    INDEX
    Explanations

    references to figures or illustrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wich
    -0.15
    å¦ĥ
    -0.14
    -thumbnails
    -0.14
     Santana
    -0.14
    riel
    -0.14
    ylon
    -0.14
     neger
    -0.14
    mans
    -0.14
    rypto
    -0.13
    gregate
    -0.13
    POSITIVE LOGITS
    head
    0.31
    heads
    0.28
    -eight
    0.20
    tte
    0.19
    .fig
    0.18
    ürlich
    0.18
    headed
    0.17
     prominently
    0.16
    antes
    0.16
    ural
    0.16
    Act Density 0.032%

    No Known Activations