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

    Neuronpedia

    INDEX
    Explanations

    names that contain the string "Anon" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    the letter "n"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.64
     welf
    -0.63
     unsupported
    -0.61
     otherwise
    -0.61
     compe
    -0.60
     DRAG
    -0.59
     caution
    -0.58
     laun
    -0.57
     Wasteland
    -0.56
     Ãľ
    -0.56
    POSITIVE LOGITS
    uggets
    1.20
    ovation
    1.12
    aturally
    1.11
    ucle
    1.09
    vironment
    1.08
    orthern
    1.08
    ihil
    1.05
    umerous
    1.05
    ounced
    1.02
    aughty
    0.98
    Act Density 0.057%

    No Known Activations