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

    Neuronpedia

    INDEX
    Explanations

    references to "SU" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to SUVs and their specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ferdinand
    -0.76
     Turks
    -0.70
    flies
    -0.69
    working
    -0.68
     Lyme
    -0.64
    wright
    -0.63
    orius
    -0.63
    ograms
    -0.61
    iard
    -0.60
    ãĤ¡
    -0.60
    POSITIVE LOGITS
    FFER
    1.07
    ITS
    0.97
    pper
    0.95
    SU
    0.95
    JO
    0.88
    arez
    0.87
    pped
    0.87
    vant
    0.86
    pling
    0.86
    pees
    0.86
    Act Density 0.004%

    No Known Activations