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

    Neuronpedia

    INDEX
    Explanations

    instances of furniture and design elements in descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    каÑĤ
    -0.14
    cott
    -0.13
    ÄĻki
    -0.13
    ãĥĦ
    -0.13
    нож
    -0.12
    rescia
    -0.12
    ÅĻÃŃž
    -0.12
    .styleable
    -0.12
    ÑĨÑĭ
    -0.12
    ÅĻel
    -0.12
    POSITIVE LOGITS
    -ch
    0.98
     CH
    0.90
    -Ch
    0.89
    CH
    0.81
    Ch
    0.80
    _ch
    0.79
    .ch
    0.78
    (ch
    0.75
    /ch
    0.74
    ch
    0.73
    Act Density 1.013%

    No Known Activations