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

    Neuronpedia

    INDEX
    Explanations

    the word "Our" when capitalized

    oai_token-act-pair · gpt-3.5-turbo

    references to specific numerical values and statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uti
    -0.72
    ila
    -0.57
    idel
    -0.54
    rots
    -0.54
    rence
    -0.53
    ills
    -0.51
     Joshua
    -0.51
     sqor
    -0.50
    wcs
    -0.50
    ola
    -0.50
    POSITIVE LOGITS
    -
    1.29
    -'
    1.11
    _>
    1.06
    âĢij
    1.04
    -)
    0.98
    ÙĴ
    0.96
    -(
    0.95
    -$
    0.94
    -|
    0.94
    -.
    0.93
    Act Density 0.213%

    No Known Activations