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

    Neuronpedia

    INDEX
    Explanations

    words related to financial increases or improvements

    oai_token-act-pair · gpt-3.5-turbo

    discussions of increases or raises in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abase
    -0.71
    eren
    -0.68
    nown
    -0.66
    emo
    -0.65
     partition
    -0.62
    hent
    -0.61
    coded
    -0.59
     Discord
    -0.58
     Hate
    -0.57
    com
    -0.56
    POSITIVE LOGITS
     raises
    3.62
     raise
    2.29
     Raise
    1.78
     raised
    1.73
     lowers
    1.59
    raise
    1.59
     raising
    1.59
     begs
    1.49
     rises
    1.43
     boosts
    1.38
    Act Density 0.010%

    No Known Activations