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

    Neuronpedia

    INDEX
    Explanations

    concepts related to physics and energy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Burr
    -0.17
    rient
    -0.17
    ixer
    -0.15
     unfold
    -0.15
    arseille
    -0.15
     Struct
    -0.14
    iesel
    -0.14
    æ·
    -0.14
    unfold
    -0.14
     ÑĢÑĥб
    -0.14
    POSITIVE LOGITS
     acceleration
    0.25
     acceler
    0.24
     conservation
    0.23
     motion
    0.21
     Acceler
    0.21
     Forces
    0.20
     SI
    0.20
     Conservation
    0.20
     accelerating
    0.20
     mass
    0.20
    Act Density 0.073%

    No Known Activations