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

    Neuronpedia

    INDEX
    Explanations

    elements related to spatial structures and orientations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    punkt
    -0.15
    (es
    -0.15
    uations
    -0.15
    ansas
    -0.14
    алÑĮне
    -0.14
    uable
    -0.14
     th
    -0.14
    ermen
    -0.14
    OLUTION
    -0.13
     fois
    -0.13
    POSITIVE LOGITS
     la
    0.24
     el
    0.19
     una
    0.18
     un
    0.17
     les
    0.16
    ìį¨
    0.16
    ween
    0.15
    ankan
    0.15
     åĨĨ
    0.15
    æı
    0.15
    Act Density 0.081%

    No Known Activations