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

    Neuronpedia

    INDEX
    Explanations

    references to specific historical or temporal contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to past events or historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    2015
    -0.81
    Dialogue
    -0.81
    IDA
    -0.78
    2018
    -0.77
    2017
    -0.76
    2016
    -0.75
     tonight
    -0.74
     2017
    -0.74
     2018
    -0.73
    CHAT
    -0.73
    POSITIVE LOGITS
     existed
    0.79
     outnumbered
    0.76
     mattered
    0.74
     consisted
    0.69
     segregated
    0.66
     WAS
    0.66
     ration
    0.66
    pired
    0.66
     Newsp
    0.65
     primitive
    0.64
    Act Density 1.352%

    No Known Activations