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

    Neuronpedia

    INDEX
    Explanations

    phrases related to warnings or predictions about future events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicative of foreboding or predictions about events, particularly related to elections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ussions
    -0.59
     occurrences
    -0.54
     snippets
    -0.52
    ussia
    -0.50
     seasons
    -0.49
     Collider
    -0.49
    nces
    -0.48
    thro
    -0.48
    imates
    -0.48
     externalToEVAOnly
    -0.47
    POSITIVE LOGITS
    uren
    0.50
    eneg
    0.49
    âĺ
    0.49
    л
    0.48
    bern
    0.47
    older
    0.47
    hew
    0.47
    âĹ
    0.46
    ressed
    0.46
    oul
    0.46
    Act Density 0.813%

    No Known Activations