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

    Neuronpedia

    INDEX
    Explanations

    references to temperature or thermodynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -1.17
     themſelves
    -0.98
     Beſ
    -0.96
    ſelves
    -0.96
    ſelf
    -0.94
     ſever
    -0.94
     ſel
    -0.91
     ſeveral
    -0.91
     ―――――
    -0.90
     Anſ
    -0.89
    POSITIVE LOGITS
     T
    2.08
    T
    1.80
     t
    1.71
    getT
    1.31
    pT
    1.08
     M
    1.04
    cT
    1.03
     S
    1.03
    mT
    1.00
     Т
    1.00
    Act Density 0.176%

    No Known Activations