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

    Neuronpedia

    INDEX
    Explanations

    adjectives and nouns related to object qualities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "verse," indicating a focus on discussions related to verses or stanzas, likely in a poetic or literary context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urated
    -0.86
    icum
    -0.85
    arij
    -0.83
    netflix
    -0.78
    abit
    -0.76
    uracy
    -0.76
    aul
    -0.75
    orem
    -0.74
    rera
    -0.74
    itated
    -0.74
    POSITIVE LOGITS
    terday
    0.77
    theless
    0.77
    verse
    0.72
    bow
    0.70
    lihood
    0.68
     Rutherford
    0.68
    Mania
    0.67
    xon
    0.66
    mbol
    0.64
    engers
    0.64
    Act Density 0.037%

    No Known Activations