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

    Neuronpedia

    INDEX
    Explanations

    references to the word "Saratoga" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tail
    -0.17
    iard
    -0.16
     possibilities
    -0.16
    aan
    -0.15
    esy
    -0.15
    amd
    -0.15
     latter
    -0.15
    ureau
    -0.15
    erty
    -0.14
    293
    -0.14
    POSITIVE LOGITS
    aje
    0.26
    acen
    0.26
    cast
    0.22
    avana
    0.21
    isbury
    0.20
    coma
    0.20
    apult
    0.19
    аÑĤов
    0.18
    azen
    0.18
    ivec
    0.18
    Act Density 0.007%

    No Known Activations