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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to mathematical concepts and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mech
    -0.15
     dane
    -0.14
    ende
    -0.14
    ILLE
    -0.14
    (patch
    -0.13
    å¯Ĵ
    -0.13
    oten
    -0.13
    aris
    -0.13
    obe
    -0.13
    ħ§
    -0.13
    POSITIVE LOGITS
     energies
    0.19
     Energy
    0.19
     energy
    0.19
     vari
    0.19
     energetic
    0.18
     ENERGY
    0.18
     var
    0.17
     mountain
    0.17
     minimizing
    0.17
     mÃŃn
    0.17
    Act Density 0.062%

    No Known Activations