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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate recognition or acknowledgement of individuals' achievements or contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    earn
    -0.15
    emy
    -0.15
     Anth
    -0.15
    znik
    -0.15
    ereum
    -0.15
     Zd
    -0.14
    .uni
    -0.14
     ÙħØ´
    -0.14
    łí
    -0.14
    ÑĢол
    -0.14
    POSITIVE LOGITS
     now
    0.15
    kah
    0.15
    eva
    0.15
    uvo
    0.14
     dzi
    0.14
    Ñıд
    0.14
    otope
    0.14
    arl
    0.14
    ehen
    0.14
    .Commit
    0.13
    Act Density 0.178%

    No Known Activations