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

    Neuronpedia

    INDEX
    Explanations

    phrases that express relationships and emotional responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    poi
    -0.16
    untu
    -0.15
    emat
    -0.14
    embr
    -0.14
    aida
    -0.14
    Ķ
    -0.14
     pornos
    -0.14
     passphrase
    -0.14
    avior
    -0.14
     DISCLAIM
    -0.14
    POSITIVE LOGITS
    auses
    0.16
    oteca
    0.15
    eyer
    0.15
    ÑĪка
    0.14
    aley
    0.14
     stát
    0.13
    íĴ
    0.13
    thon
    0.13
    cház
    0.13
    149
    0.13
    Act Density 1.263%

    No Known Activations