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

    Neuronpedia

    INDEX
    Explanations

    titles or headings within text

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the word "MORE."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vet
    -0.79
    aper
    -0.79
    stood
    -0.78
    arist
    -0.78
    riber
    -0.76
    liest
    -0.74
    etime
    -0.72
    reen
    -0.71
    ibel
    -0.71
    ee
    -0.71
    POSITIVE LOGITS
    MORE
    1.13
    HEAD
    0.93
     than
    0.88
     ado
    0.86
    agascar
    0.83
    FTWARE
    0.79
     convol
    0.76
     VIDEOS
    0.76
     MORE
    0.76
     ABOUT
    0.74
    Act Density 0.005%

    No Known Activations