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

    Neuronpedia

    INDEX
    Explanations

    Italian words and names

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or personal names in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ARC
    -0.58
    Indiana
    -0.57
     Shock
    -0.57
    ANY
    -0.57
     Rutherford
    -0.56
     Chambers
    -0.56
    FT
    -0.55
    NetMessage
    -0.55
    eal
    -0.54
    Michigan
    -0.54
    POSITIVE LOGITS
    quer
    0.95
    iage
    0.87
    unci
    0.84
    jen
    0.78
    ç
    0.77
    vae
    0.77
    nu
    0.76
    Ä
    0.76
    quet
    0.75
     los
    0.74
    Act Density 0.123%

    No Known Activations