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

    Neuronpedia

    INDEX
    Explanations

    phrases related to thermodynamic processes and energy work

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     []:
    -0.54
     gantung
    -0.50
    Біографія
    -0.47
    apimachinery
    -0.44
    autorest
    -0.43
     /*#__
    -0.43
     addirittura
    -0.43
    хьтан
    -0.42
    年後
    -0.42
    مقاله
    -0.41
    POSITIVE LOGITS
     energy
    0.70
    energy
    0.64
    Energy
    0.60
     Energy
    0.57
     heat
    0.57
     ENERGY
    0.56
    Jou
    0.54
     énergé
    0.53
     Energie
    0.53
    ENERGY
    0.52
    Act Density 0.788%

    No Known Activations