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

    Neuronpedia

    INDEX
    Explanations

    terms related to collaboration and partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yan
    -0.15
    ä¸ĸç´Ģ
    -0.15
    owie
    -0.15
    raz
    -0.15
    erm
    -0.14
    tram
    -0.14
    kinci
    -0.14
    ISIBLE
    -0.13
     gridColumn
    -0.13
    aub
    -0.13
    POSITIVE LOGITS
    215
    0.15
    chas
    0.14
    emetery
    0.14
    264
    0.14
    88
    0.14
    athers
    0.14
     jadx
    0.14
    adiens
    0.13
    _ptr
    0.13
    884
    0.13
    Act Density 0.016%

    No Known Activations