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

    Neuronpedia

    INDEX
    Explanations

    words related to comparisons or contrasts expressing a higher level or degree

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating an increase or enhancement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    crow
    -0.85
    guard
    -0.77
    books
    -0.74
    elf
    -0.73
    pta
    -0.73
    breaks
    -0.72
    cker
    -0.71
    raid
    -0.71
    fing
    -0.71
    washing
    -0.68
    POSITIVE LOGITS
     than
    1.04
     appreciation
    1.02
     importance
    0.93
     pains
    0.91
     amounts
    0.90
     quantities
    0.90
     abundance
    0.89
     likelihood
    0.88
     heights
    0.86
     clarity
    0.86
    Act Density 0.018%

    No Known Activations