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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technology and computer security

    oai_token-act-pair · gpt-3.5-turbo

    numerical and procedural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plet
    -0.78
     HOU
    -0.78
    qus
    -0.73
    ischer
    -0.67
    redo
    -0.65
    ı
    -0.64
    eder
    -0.64
    kefeller
    -0.63
    wered
    -0.62
    ler
    -0.62
    POSITIVE LOGITS
    ccording
    0.97
    ãĤ´ãĥ³
    0.67
     Notwithstanding
    0.67
     Allows
    0.64
     Despite
    0.64
     Located
    0.63
    ¶
    0.62
     redund
    0.62
     Similar
    0.61
     According
    0.61
    Act Density 0.370%

    No Known Activations