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

    Neuronpedia

    INDEX
    Explanations

    links to online resources or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    937
    -0.17
    orny
    -0.17
    atorial
    -0.16
    boxed
    -0.16
    amo
    -0.16
    828
    -0.15
    rug
    -0.15
    acin
    -0.15
    acock
    -0.15
    01
    -0.15
    POSITIVE LOGITS
    ASI
    0.17
    edio
    0.15
    uddy
    0.15
    SEM
    0.14
    oste
    0.13
    .hero
    0.13
    ech
    0.13
     SW
    0.13
     NEGLIGENCE
    0.13
    еÑĤ
    0.13
    Act Density 0.045%

    No Known Activations