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

    Neuronpedia

    INDEX
    Explanations

    names, particularly names of people

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, specifically first initials followed by letters related to them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Confederation
    -0.73
    ModLoader
    -0.70
    ruary
    -0.68
     Sioux
    -0.64
     FANTASY
    -0.64
    姫
    -0.63
     Leia
    -0.61
     Cinderella
    -0.60
     Fancy
    -0.60
    */(
    -0.59
    POSITIVE LOGITS
    onson
    0.70
    adiq
    0.66
    uner
    0.66
    opol
    0.64
    isner
    0.64
    usb
    0.63
    ãĤ±
    0.63
    omin
    0.63
    arella
    0.63
    acher
    0.62
    Act Density 0.086%

    No Known Activations