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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating health conditions and discussions surrounding medical practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ~=
    -0.16
     Uncategorized
    -0.15
    財
    -0.15
    Descriptors
    -0.15
    \:
    -0.14
    Entity
    -0.13
     seper
    -0.13
     affection
    -0.13
     closer
    -0.13
     today
    -0.13
    POSITIVE LOGITS
    arget
    0.16
    imals
    0.15
    اعد
    0.15
    legg
    0.15
    psilon
    0.15
    åľ°æĸ¹
    0.15
     Sır
    0.14
    ¤íĶĦ
    0.14
    ообÑĢаз
    0.14
    iens
    0.14
    Act Density 0.207%

    No Known Activations