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

    Neuronpedia

    INDEX
    Explanations

    dashes

    oai_token-act-pair · gpt-3.5-turbo

    segments of text or phrases that contain dashes or bullet points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hass
    -0.70
    iliary
    -0.66
     Galile
    -0.65
     basil
    -0.65
     Madden
    -0.63
    ously
    -0.63
     sclerosis
    -0.62
     oun
    -0.62
     activ
    -0.61
     cavity
    -0.61
    POSITIVE LOGITS
    fuck
    0.98
    something
    0.91
    ITS
    0.90
    notes
    0.89
    lance
    0.88
    meaning
    0.87
    sil
    0.87
    like
    0.86
    requ
    0.85
    reviewed
    0.84
    Act Density 0.024%

    No Known Activations