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

    Neuronpedia

    INDEX
    Explanations

    dates specified in the format "DAY MONTH YEAR"

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and conjunctions in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thood
    -0.77
    olo
    -0.69
    izen
    -0.67
    aunted
    -0.66
    forcement
    -0.66
    ulatory
    -0.65
    obos
    -0.62
    iety
    -0.62
    antz
    -0.61
    undai
    -0.61
    POSITIVE LOGITS
     meaning
    1.08
     huh
    1.01
     whereas
    1.00
     hence
    0.94
     but
    0.88
     yeah
    0.83
     yes
    0.81
     haha
    0.80
    yet
    0.80
     Meaning
    0.79
    Act Density 0.443%

    No Known Activations