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

    Neuronpedia

    INDEX
    Explanations

    mentions related to specific years or time periods

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years or time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vae
    -0.65
    Often
    -0.64
    ggles
    -0.64
    mber
    -0.62
     fixation
    -0.62
    Recently
    -0.61
    urdy
    -0.60
     Chaser
    -0.59
    ãĤ¤ãĥĪ
    -0.59
    usual
    -0.57
    POSITIVE LOGITS
     alone
    1.54
     totaling
    1.06
     compared
    0.99
     combined
    0.94
    according
    0.89
    alone
    0.87
     according
    0.86
    *.
    0.84
     attributable
    0.82
     excluding
    0.81
    Act Density 0.212%

    No Known Activations