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

    Neuronpedia

    INDEX
    Explanations

    phrases that express strong opinions or evaluations, often using words like "hard," "better," "good," "open," "well," "sick," "welcome," "prepared," and "advised."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating difficulty or challenges in achieving something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     innocuous
    -0.67
     deform
    -0.65
     succession
    -0.64
    ulence
    -0.62
     separat
    -0.62
     combustion
    -0.61
     intimacy
    -0.61
    geries
    -0.60
     unrem
    -0.60
     Combine
    -0.59
    POSITIVE LOGITS
     aware
    1.09
     pleased
    1.09
    cerned
    1.09
     interested
    1.02
     willing
    1.01
    aware
    0.98
     obliged
    0.98
     convinced
    0.97
    interested
    0.96
     delighted
    0.96
    Act Density 0.469%

    No Known Activations