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

    Neuronpedia

    INDEX
    Explanations

    words related to specific products or brands

    oai_token-act-pair · gpt-3.5-turbo

    capital letters or acronyms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     flares
    -0.82
     flare
    -0.68
     skelet
    -0.67
     levers
    -0.66
     contrace
    -0.65
     depth
    -0.63
     attendance
    -0.62
    ãĥĻ
    -0.62
     reflection
    -0.61
    ++++++++++++++++
    -0.61
    POSITIVE LOGITS
    ée
    0.76
    ault
    0.74
    schild
    0.74
    ç
    0.74
    én
    0.73
    ï¸ı
    0.73
    ailable
    0.73
    hower
    0.72
    ois
    0.71
    é
    0.70
    Act Density 0.199%

    No Known Activations