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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to significance or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .opend
    -0.17
    uty
    -0.15
     âĹĦ
    -0.15
    AMED
    -0.15
    swire
    -0.15
    çļĦäºĭæĥħ
    -0.15
    licate
    -0.14
    pty
    -0.14
    ijn
    -0.14
    .gnu
    -0.13
    POSITIVE LOGITS
     pros
    0.15
    apesh
    0.15
    ouncer
    0.15
    اÙĪÙĬØ©
    0.15
    esson
    0.14
    OTS
    0.14
    (çģ«
    0.14
    orget
    0.13
    Void
    0.13
    ULE
    0.13
    Act Density 0.114%

    No Known Activations