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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to reality and authenticity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UCT
    -0.15
    κι
    -0.14
    CTX
    -0.14
    ÃĹ↵↵
    -0.14
    sav
    -0.14
    ebb
    -0.14
    DAT
    -0.14
    rah
    -0.13
     Vega
    -0.13
     Kens
    -0.13
    POSITIVE LOGITS
    ingly
    0.16
    سط
    0.15
    dorf
    0.15
    instein
    0.14
    RYPT
    0.14
    yle
    0.14
     Budget
    0.13
    éĮ
    0.13
    heim
    0.13
     League
    0.13
    Act Density 0.346%

    No Known Activations