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

    Neuronpedia

    INDEX
    Explanations

    occurrences of text being posted on social media or websites

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "posted."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glers
    -0.76
    kos
    -0.69
    osi
    -0.68
    ichick
    -0.67
    phant
    -0.67
    Iv
    -0.66
     Brill
    -0.65
     Galile
    -0.63
    pter
    -0.61
    ão
    -0.61
    POSITIVE LOGITS
    ulate
    0.89
     postings
    0.84
    hum
    0.84
    doctoral
    0.82
    gres
    0.80
    posted
    0.79
    uploads
    0.78
    mortem
    0.76
     posting
    0.76
     posted
    0.73
    Act Density 0.041%

    No Known Activations