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

    Neuronpedia

    INDEX
    Explanations

    references to specific geographical locations or proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angan
    -0.15
    UEL
    -0.15
    uels
    -0.15
    ived
    -0.14
    ounge
    -0.14
    .Strict
    -0.14
    uell
    -0.14
     prioritize
    -0.14
    ivos
    -0.14
    quette
    -0.13
    POSITIVE LOGITS
    bing
    0.28
    bed
    0.20
    ub
    0.20
    ilee
    0.19
    rique
    0.19
    erculosis
    0.18
    ric
    0.17
    berman
    0.17
    ernal
    0.16
    leshoot
    0.16
    Act Density 0.026%

    No Known Activations