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

    Neuronpedia

    INDEX
    Explanations

    phrases related to continuity or ongoing processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to continuation or persistence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uffle
    -0.76
    è¦ļéĨĴ
    -0.75
    ramid
    -0.74
    athing
    -0.74
    houses
    -0.74
    LCS
    -0.72
    ouls
    -0.70
    idding
    -0.70
    wich
    -0.67
    arest
    -0.67
    POSITIVE LOGITS
    contin
    1.26
     Contin
    1.17
     CONTIN
    1.09
     contin
    1.09
     continuation
    1.04
     continu
    0.96
    uality
    0.95
     continuity
    0.94
    uations
    0.92
     Continued
    0.91
    Act Density 0.009%

    No Known Activations