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

    Neuronpedia

    INDEX
    Explanations

    instances of dates or numerical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oter
    -0.17
    ippers
    -0.15
    alis
    -0.15
    jk
    -0.15
    er
    -0.15
    288
    -0.15
    elled
    -0.14
    gan
    -0.14
     Bark
    -0.14
    aliz
    -0.14
    POSITIVE LOGITS
    Ả
    0.16
    ãģ¤ãģij
    0.15
    ORY
    0.15
    CPF
    0.14
     taÅŁÄ±n
    0.14
    GRE
    0.14
    YD
    0.14
     independent
    0.14
    /A
    0.13
    á»ķ
    0.13
    Act Density 0.014%

    No Known Activations