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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a significant amount of time has passed

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating durations of time or experiences characterized by the word "of"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anooga
    -0.84
    ÙIJ
    -0.76
    ombies
    -0.73
    cn
    -0.73
    named
    -0.69
    deck
    -0.69
    orah
    -0.69
    paces
    -0.67
    PI
    -0.67
    epad
    -0.66
    POSITIVE LOGITS
     uninterrupted
    1.07
     campaigning
    0.95
     accumulated
    0.91
     struggle
    0.88
     stagnation
    0.87
     accumulating
    0.86
     unsuccessful
    0.85
     continuous
    0.85
     frustration
    0.85
     silence
    0.84
    Act Density 0.063%

    No Known Activations