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

    Neuronpedia

    INDEX
    Explanations

    expressions related to the concept of forgetting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holding
    -0.15
     Bracket
    -0.14
    388
    -0.14
    549
    -0.14
    èİ
    -0.14
    entarios
    -0.14
    _Impl
    -0.13
    ãİ
    -0.13
    hydrate
    -0.13
    oret
    -0.13
    POSITIVE LOGITS
    ews
    0.17
    amus
    0.17
    maf
    0.15
    ÑĥÑĩаÑģ
    0.15
    ä½ľ
    0.14
    ppv
    0.14
    velt
    0.14
    anes
    0.14
     crim
    0.14
    ath
    0.13
    Act Density 0.013%

    No Known Activations