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

    Neuronpedia

    INDEX
    Explanations

    concepts related to energy and forces in physical systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unprotected
    -0.16
    ÙĤØ·
    -0.15
    .Override
    -0.15
    blick
    -0.15
    ENO
    -0.14
    iquid
    -0.14
    UZ
    -0.14
    sher
    -0.13
    omik
    -0.13
    å®
    -0.13
    POSITIVE LOGITS
     energy
    0.45
    energy
    0.40
     Energy
    0.36
     ENERGY
    0.34
    -energy
    0.33
    Energy
    0.32
    .energy
    0.32
    _energy
    0.31
    nergy
    0.30
     energies
    0.28
    Act Density 0.099%

    No Known Activations