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

    Neuronpedia

    INDEX
    Explanations

    expressions of time sequence

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    aez
    -0.80
    女
    -0.75
    cin
    -0.71
    cci
    -0.71
    Tur
    -0.68
    enf
    -0.67
    ãĥ³ãĤ¸
    -0.67
    voy
    -0.67
    uci
    -0.67
     constitu
    -0.66
    POSITIVE LOGITS
    noon
    1.23
    math
    1.06
    wards
    1.00
     completing
    0.98
    market
    0.96
    words
    0.93
     defeating
    0.90
     completion
    0.89
     discovering
    0.88
    thought
    0.88
    Act Density 2.145%

    No Known Activations