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

    Neuronpedia

    INDEX
    Explanations

    dates and times in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     spo
    -0.69
     unbeat
    -0.68
     undis
    -0.65
     quir
    -0.64
     behav
    -0.64
    ãĥ«
    -0.63
     scripting
    -0.62
    Ł
    -0.62
     defe
    -0.61
     skelet
    -0.61
    POSITIVE LOGITS
     EDT
    0.93
     Retrieved
    0.79
    endment
    0.78
     EST
    0.78
    dylib
    0.75
     PST
    0.74
     PDT
    0.73
     ET
    0.72
     PT
    0.71
    ansion
    0.71
    Act Density 0.042%

    No Known Activations