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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to the physical characteristics or qualities of objects

    oai_token-act-pair · gpt-3.5-turbo

    descriptive adjectives related to size and quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vantage
    -1.02
    cture
    -0.84
    plementation
    -0.82
    emark
    -0.81
    BIP
    -0.80
    wark
    -0.79
    someone
    -0.78
    ittee
    -0.78
    position
    -0.77
    enario
    -0.76
    POSITIVE LOGITS
     versions
    1.14
     batches
    1.08
     bursts
    1.07
     chunks
    1.06
     clusters
    1.02
     pieces
    0.99
     plots
    0.99
     loops
    0.97
     doses
    0.96
     piles
    0.96
    Act Density 0.349%

    No Known Activations