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

    Neuronpedia

    INDEX
    Explanations

    programming terminology related to tokenization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rost
    -0.18
    /fw
    -0.18
    lander
    -0.17
    ustin
    -0.16
    ude
    -0.16
     بÙĪابة
    -0.15
    een
    -0.15
    ening
    -0.15
    OwnProperty
    -0.14
    ened
    -0.14
    POSITIVE LOGITS
    ized
    0.20
    holder
    0.19
    hell
    0.18
    neau
    0.17
    age
    0.16
    armac
    0.16
    omics
    0.15
    icia
    0.15
    holders
    0.15
    swana
    0.15
    Act Density 0.053%

    No Known Activations