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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "just" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the words "just" and "even."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orse
    -0.71
    ornia
    -0.69
    PRES
    -0.69
    versible
    -0.67
    ricted
    -0.67
    hal
    -0.66
    uart
    -0.65
    KEN
    -0.65
    emale
    -0.64
    Female
    -0.63
    POSITIVE LOGITS
     begs
    0.74
     importantly
    0.68
     anecd
    0.64
     behold
    0.64
     luck
    0.63
     worries
    0.62
     disclaimer
    0.61
     prest
    0.61
     fortun
    0.61
     symbolism
    0.60
    Act Density 0.245%

    No Known Activations