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

    Neuronpedia

    INDEX
    Explanations

    elements related to accommodation and room features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gard
    -0.17
     Bad
    -0.16
    cox
    -0.15
    orners
    -0.15
    inux
    -0.15
    brick
    -0.15
    ông
    -0.15
    Bad
    -0.14
    lasses
    -0.14
    bard
    -0.14
    POSITIVE LOGITS
    upert
    0.16
     Helm
    0.14
     Sit
    0.14
     Xã
    0.14
    ISHED
    0.14
    ropoda
    0.14
    ozici
    0.14
     helm
    0.14
     HEAP
    0.14
    æĹħ
    0.13
    Act Density 0.011%

    No Known Activations