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

    Neuronpedia

    INDEX
    Explanations

    references to broadly defined concepts or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dün
    -0.16
    .scalablytyped
    -0.15
     Nachricht
    -0.15
    ylie
    -0.15
     nackte
    -0.15
    ynn
    -0.14
    ogo
    -0.14
    ndon
    -0.14
    shan
    -0.14
    ibri
    -0.14
    POSITIVE LOGITS
    aspect
    0.16
    comings
    0.15
    ardware
    0.14
    vens
    0.14
     aspect
    0.14
    gid
    0.14
    æĿ¾
    0.14
    вай
    0.14
    ifar
    0.14
    irtual
    0.13
    Act Density 0.032%

    No Known Activations