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

    Neuronpedia

    INDEX
    Explanations

    references to various types of fruit

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    poons
    -0.16
    idon
    -0.15
    èijī
    -0.15
    hart
    -0.15
    enta
    -0.14
    249
    -0.14
    ihan
    -0.14
    hare
    -0.14
    atics
    -0.14
    jÅ¡ÃŃ
    -0.14
    POSITIVE LOGITS
    fulness
    0.24
    cake
    0.21
    fully
    0.20
    -tree
    0.18
     juice
    0.18
    anyl
    0.17
    rea
    0.17
    /apple
    0.16
    FUL
    0.16
     juices
    0.16
    Act Density 0.020%

    No Known Activations