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

    Neuronpedia

    INDEX
    Explanations

    references to different types of flat surfaces or flat objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    him
    -0.17
    holes
    -0.17
    iest
    -0.17
    ahr
    -0.15
    iams
    -0.15
     بزر
    -0.15
    aan
    -0.15
    hole
    -0.15
    RIX
    -0.15
    iya
    -0.15
    POSITIVE LOGITS
    ulence
    0.40
    ulent
    0.35
    iron
    0.28
    bed
    0.25
    ness
    0.25
    ting
    0.25
    foot
    0.24
    lining
    0.23
    buffers
    0.23
    bread
    0.23
    Act Density 0.008%

    No Known Activations