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

    Neuronpedia

    INDEX
    Explanations

    the word "as" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upt
    -0.72
    oller
    -0.71
    lish
    -0.69
    obyl
    -0.69
    ople
    -0.66
    ools
    -0.65
    stall
    -0.65
    Ò
    -0.64
    rir
    -0.61
    oqu
    -0.61
    POSITIVE LOGITS
     regards
    1.39
     evidenced
    1.14
    pects
    1.03
    piring
    0.95
     opposed
    0.94
     soon
    0.94
    pired
    0.88
     well
    0.85
     contrasted
    0.84
    pires
    0.81
    Act Density 0.089%

    No Known Activations