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

    Neuronpedia

    INDEX
    Explanations

    sentences that introduce or discuss different topics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ·ãĥ£
    -0.67
    ctors
    -0.62
     srf
    -0.57
    ĪĴ
    -0.56
    idth
    -0.54
    Weather
    -0.53
     Tro
    -0.53
    ao
    -0.52
     Crush
    -0.52
    ãĥ«
    -0.51
    POSITIVE LOGITS
     anyway
    0.99
     anyways
    0.98
     aloud
    0.96
     yourself
    0.94
     ourselves
    0.93
     myself
    0.93
     firsthand
    0.91
     ASAP
    0.89
     herself
    0.88
     anonymously
    0.86
    Act Density 5.822%

    No Known Activations