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

    Neuronpedia

    INDEX
    Explanations

    references to significant historical figures and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    engin
    -0.16
    awah
    -0.16
     Anglic
    -0.16
    sburg
    -0.15
    arrass
    -0.15
    å¹¹ç·ļ
    -0.15
    ë¡
    -0.15
    çĤ®
    -0.14
    bish
    -0.14
    andal
    -0.14
    POSITIVE LOGITS
     Athens
    0.31
     Spartan
    0.28
     Athen
    0.28
     hop
    0.25
     Lesbian
    0.25
     Marathon
    0.24
     Greek
    0.24
     Greece
    0.23
     Lesb
    0.23
    hop
    0.22
    Act Density 0.050%

    No Known Activations