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

    Neuronpedia

    INDEX
    Explanations

    phrases that express preference or desire for past experiences or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akis
    -0.17
    chten
    -0.14
     gonna
    -0.14
    unused
    -0.14
    HK
    -0.14
    yll
    -0.14
    itis
    -0.14
     ($.
    -0.14
    nable
    -0.14
    chte
    -0.14
    POSITIVE LOGITS
     originally
    0.16
    okens
    0.16
    ption
    0.15
    Originally
    0.15
    ок
    0.14
    OCR
    0.14
    BeNull
    0.14
    los
    0.14
    495
    0.14
    iddet
    0.14
    Act Density 0.129%

    No Known Activations