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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases or comparisons

    oai_token-act-pair · gpt-3.5-turbo

    the word "as" used in various contexts to indicate roles or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oller
    -0.72
    eor
    -0.64
    ega
    -0.62
    BACK
    -0.62
    rost
    -0.59
    rol
    -0.58
    rolet
    -0.58
    ople
    -0.58
    Kent
    -0.58
     snag
    -0.57
    POSITIVE LOGITS
     opposed
    1.13
    pires
    1.04
     well
    0.98
    pired
    0.97
     regards
    0.96
    ylum
    0.94
    pects
    0.93
    phalt
    0.92
    part
    0.92
     evidenced
    0.91
    Act Density 0.196%

    No Known Activations