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

    Neuronpedia

    INDEX
    Explanations

    demonstrative pronouns and references suggesting specificity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Oswald
    -0.17
    Constraints
    -0.16
    eti
    -0.16
     Trap
    -0.14
    ãģ¡ãĤĩ
    -0.14
    ansi
    -0.14
    OTA
    -0.14
    åĪ©
    -0.14
    amar
    -0.14
     Elder
    -0.14
    POSITIVE LOGITS
    edio
    0.15
    pek
    0.15
    ione
    0.15
    emap
    0.15
    .insertBefore
    0.15
    ILING
    0.15
    endo
    0.14
    olve
    0.14
    ioneer
    0.14
    alet
    0.14
    Act Density 0.006%

    No Known Activations