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

    Neuronpedia

    INDEX
    Explanations

    links or references to additional content below the main text

    oai_token-act-pair · gpt-3.5-turbo

    references to content or items mentioned in subsequent sections of the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥı
    -0.77
    oka
    -0.75
    ãĤ£
    -0.74
    éŃĶ
    -0.72
    MM
    -0.72
    olly
    -0.71
    eg
    -0.69
    imm
    -0.68
    olid
    -0.66
    Deal
    -0.65
    POSITIVE LOGITS
    below
    0.85
     below
    0.80
    ground
    0.79
    eatures
    0.74
     tradem
    0.71
    tics
    0.70
    neath
    0.69
     summar
    0.67
     trending
    0.66
     markup
    0.66
    Act Density 0.024%

    No Known Activations