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

    Neuronpedia

    INDEX
    Explanations

    groups of people or entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that begin with "a group of" followed by a count or descriptor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akedown
    -0.74
    cape
    -0.68
    ibe
    -0.67
    turn
    -0.66
    lycer
    -0.66
    ukong
    -0.65
    lly
    -0.64
    asta
    -0.63
     prescribe
    -0.62
    xtap
    -0.61
    POSITIVE LOGITS
     sorts
    0.93
     individuals
    0.85
     friends
    0.82
     adventurers
    0.80
     kindred
    0.80
     fellow
    0.78
     explorers
    0.78
     thinkers
    0.77
     professionals
    0.77
     volunteers
    0.77
    Act Density 0.117%

    No Known Activations