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

    Neuronpedia

    INDEX
    Explanations

    mentions of people or names, specifically those starting with the letter "D"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ump
    -0.21
    ock
    -0.20
    ocs
    -0.17
    ays
    -0.17
    iesel
    -0.17
    ocking
    -0.16
    ATA
    -0.16
    raw
    -0.16
    uner
    -0.16
    agger
    -0.15
    POSITIVE LOGITS
    arry
    0.22
    eric
    0.21
    aron
    0.21
    omen
    0.20
    anel
    0.20
    yll
    0.19
    arr
    0.19
    erval
    0.18
    IMIT
    0.18
    hire
    0.18
    Act Density 0.028%

    No Known Activations