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

    Neuronpedia

    INDEX
    Explanations

    references to enclosures or confinement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oma
    -0.17
    ома
    -0.15
     Giov
    -0.15
    ouch
    -0.15
    sie
    -0.14
    ylko
    -0.14
    tru
    -0.14
    setting
    -0.14
    usted
    -0.14
    ãĥ³ãĥĨãĤ£
    -0.14
    POSITIVE LOGITS
    nett
    0.16
    altar
    0.16
    æı
    0.15
     Cout
    0.15
    arsed
    0.15
    itch
    0.15
    æŃ
    0.15
    IRON
    0.14
     entrance
    0.14
    ords
    0.14
    Act Density 0.005%

    No Known Activations