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

    Neuronpedia

    INDEX
    Explanations

    comparisons indicating something has reached a peak or is at an all-time high

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating increasing levels of something over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ename
    -0.72
     Cosponsors
    -0.66
    anchester
    -0.64
    heimer
    -0.62
     resemb
    -0.61
    ificantly
    -0.60
     Parables
    -0.60
     reconc
    -0.59
    rera
    -0.59
    ochet
    -0.58
    POSITIVE LOGITS
     before
    1.32
    before
    1.15
     BEFORE
    1.07
     dreamed
    0.88
     Before
    0.83
     imagined
    0.81
     imaginable
    0.79
     anticipated
    0.78
     ago
    0.78
     thanks
    0.77
    Act Density 0.039%

    No Known Activations