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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntactical structures or keywords

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    631
    -0.18
     Sparks
    -0.15
    onn
    -0.15
     Io
    -0.14
    eny
    -0.14
     quadr
    -0.14
     Gro
    -0.14
    串
    -0.14
    lad
    -0.14
    pit
    -0.14
    POSITIVE LOGITS
    ocre
    0.15
    FORMANCE
    0.15
     chilled
    0.14
    icias
    0.14
    bose
    0.14
    SetName
    0.14
    ****/↵
    0.14
     datastore
    0.14
    dress
    0.14
    indrome
    0.14
    Act Density 0.073%

    No Known Activations