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

    Neuronpedia

    INDEX
    Explanations

    instances where the phrase "in other words" appears in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference alternative viewpoints or different perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.66
    iste
    -0.63
    issance
    -0.62
     outweigh
    -0.61
    avorite
    -0.60
    Always
    -0.59
    akery
    -0.59
     overcame
    -0.58
    Accept
    -0.57
    winning
    -0.56
    POSITIVE LOGITS
    worldly
    1.27
    words
    1.01
     respects
    0.99
     words
    0.92
    wise
    0.86
     contexts
    0.85
     instances
    0.82
     areas
    0.81
     languages
    0.78
     places
    0.77
    Act Density 0.024%

    No Known Activations