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

    Neuronpedia

    INDEX
    Explanations

    elements related to academic citations and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eldom
    -0.16
    /story
    -0.14
    ackbar
    -0.14
     Schmidt
    -0.14
     ÑĤи
    -0.13
    éļ
    -0.13
     FACT
    -0.13
    æĸ½å·¥
    -0.13
     Garland
    -0.13
     Roles
    -0.13
    POSITIVE LOGITS
    ruc
    0.19
     steering
    0.16
     èĩ
    0.15
    vů
    0.15
    chia
    0.15
     è©ķ
    0.14
    éri
    0.14
    review
    0.14
    ometr
    0.14
    Receive
    0.14
    Act Density 0.052%

    No Known Activations