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

    Neuronpedia

    INDEX
    Explanations

    affirmative responses to inquiries and confirmations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ïħνα
    -0.15
    airo
    -0.15
     Sparse
    -0.15
    lik
    -0.14
    ierce
    -0.14
    istine
    -0.14
    Sparse
    -0.14
    ask
    -0.14
     CancellationToken
    -0.14
    villa
    -0.14
    POSITIVE LOGITS
    berman
    0.16
    ê¸Ģ
    0.16
    odyn
    0.15
     iota
    0.15
    kommen
    0.15
    arth
    0.14
    æļ®
    0.14
    zk
    0.14
    igrams
    0.14
     воÑģп
    0.14
    Act Density 0.051%

    No Known Activations