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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to being "hot" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "}")
    -1.15
    )");
    -1.10
    urized
    -0.97
    "]]
    -0.97
    脚注の使い方
    -0.96
    CreateMap
    -0.94
    তথ্যসূত্র
    -0.94
    "}"
    -0.94
     raiſ
    -0.94
     TextAlign
    -0.93
    POSITIVE LOGITS
     HOT
    1.12
     hot
    1.09
     Hot
    1.07
    Hot
    1.07
    hot
    1.02
    HOT
    1.01
    ot
    0.80
    pot
    0.77
    e
    0.76
    chot
    0.75
    Act Density 0.072%

    No Known Activations