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

    Neuronpedia

    INDEX
    Explanations

    references to notable achievements or descriptors associated with people or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    est
    -0.18
    igkeit
    -0.17
    sst
    -0.16
    ylene
    -0.15
    mere
    -0.15
    aset
    -0.14
    ecast
    -0.14
    ements
    -0.14
     Preston
    -0.14
    bras
    -0.14
    POSITIVE LOGITS
    adal
    0.16
    akat
    0.16
    .Xaml
    0.15
    æĶ¶å½ķ
    0.15
    olem
    0.14
    iden
    0.14
    _ASSUME
    0.14
     Zem
    0.14
    \Persistence
    0.14
     wed
    0.14
    Act Density 0.020%

    No Known Activations