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

    Neuronpedia

    INDEX
    Explanations

    times when actions are taken by groups of people, such as communities or populations

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with societal dynamics and the general public

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    door
    -0.76
    talk
    -0.70
    ramid
    -0.68
    gered
    -0.66
    cell
    -0.66
    amy
    -0.66
    verbs
    -0.64
    finished
    -0.64
    ki
    -0.63
    vals
    -0.62
    POSITIVE LOGITS
    ments
    1.02
    enance
    0.82
    entimes
    0.80
    ively
    0.77
    ment
    0.75
    ally
    0.74
    igious
    0.70
    estinal
    0.69
     therein
    0.67
    tainment
    0.67
    Act Density 0.381%

    No Known Activations