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

    Neuronpedia

    INDEX
    Explanations

    words related to being motivated or influenced by something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "inspired"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nda
    -0.72
    ulla
    -0.66
    lower
    -0.65
     Gamble
    -0.64
    bage
    -0.63
    zero
    -0.62
    pps
    -0.61
     bargaining
    -0.61
    Fact
    -0.61
    slot
    -0.61
    POSITIVE LOGITS
     inspired
    3.65
     Inspired
    2.58
    inspired
    2.43
     inspiration
    2.10
    Insp
    2.00
     influenced
    1.98
     inspir
    1.80
     inspires
    1.79
     motivated
    1.78
     inspire
    1.77
    Act Density 0.013%

    No Known Activations