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

    Neuronpedia

    INDEX
    Explanations

    terms related to physics and physicists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Arb
    -0.16
     Vig
    -0.15
     Guards
    -0.14
     Gard
    -0.14
     bye
    -0.14
    ánh
    -0.14
     ho
    -0.13
    spir
    -0.13
    itchens
    -0.13
    ————————
    -0.13
    POSITIVE LOGITS
    reau
    0.16
    ubar
    0.15
    eno
    0.15
    RIPT
    0.14
    ollo
    0.14
    fully
    0.14
    _Impl
    0.14
    udder
    0.13
    vr
    0.13
     Tribe
    0.13
    Act Density 0.014%

    No Known Activations