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

    Neuronpedia

    INDEX
    Explanations

    phrases related to uniqueness and significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    акÑģим
    -0.16
    aks
    -0.15
    umes
    -0.15
    azole
    -0.14
    antes
    -0.14
    acket
    -0.14
    emales
    -0.14
    ÐĴÑĤ
    -0.14
    .EventHandler
    -0.14
    å¯
    -0.14
    POSITIVE LOGITS
     Klo
    0.17
    ubits
    0.15
     prem
    0.15
     Toll
    0.15
    ozor
    0.14
    ucer
    0.14
    askell
    0.14
     unlike
    0.14
    bots
    0.14
    erras
    0.14
    Act Density 0.127%

    No Known Activations