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

    Neuronpedia

    INDEX
    Explanations

    references to role-playing games (RPGs) and character preferences in gaming

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Khart
    -1.67
     dises
    -1.64
     Juf
    -1.63
     Keny
    -1.59
     sovere
    -1.57
     fta
    -1.57
     Augu
    -1.53
     Confu
    -1.51
     volunte
    -1.49
     thut
    -1.49
    POSITIVE LOGITS
    <bos>
    1.11
     my
    1.00
     myself
    0.84
     me
    0.73
     meine
    0.72
     mijn
    0.71
     I
    0.67
    domada
    0.66
    我的
    0.66
     lately
    0.65
    Act Density 0.963%

    No Known Activations