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

    Neuronpedia

    INDEX
    Explanations

    phrases that refer to specific cases or instances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lie
    -0.17
     wag
    -0.15
    egas
    -0.15
    arrants
    -0.15
    king
    -0.15
    sb
    -0.15
    sel
    -0.14
     fuse
    -0.14
     Kingdom
    -0.14
    ikh
    -0.14
    POSITIVE LOGITS
     case
    0.16
    ulary
    0.15
    rowave
    0.15
    isphere
    0.14
    ipline
    0.14
    Sharper
    0.14
    uais
    0.14
    coon
    0.14
    -Mart
    0.14
    zik
    0.14
    Act Density 0.089%

    No Known Activations