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

    Neuronpedia

    INDEX
    Explanations

    words related to usefulness and utility

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "useful" and its synonyms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uph
    -0.68
    opers
    -0.68
    agate
    -0.65
    Fight
    -0.65
     Alive
    -0.63
    olition
    -0.62
     boarded
    -0.62
    rollers
    -0.61
    eve
    -0.61
    Vision
    -0.61
    POSITIVE LOGITS
     idiots
    1.14
     adjunct
    0.93
     tools
    0.85
     insights
    0.84
     information
    0.82
    tips
    0.79
     inform
    0.79
     insight
    0.79
     tool
    0.78
    iences
    0.76
    Act Density 0.045%

    No Known Activations