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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    frequent references to male and female characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    INESS
    -0.69
    problem
    -0.68
    veyard
    -0.68
    pite
    -0.64
     Millennium
    -0.61
     Panc
    -0.60
    population
    -0.59
    ¿½
    -0.59
     hindsight
    -0.59
    growth
    -0.58
    POSITIVE LOGITS
    'll
    1.39
    'd
    1.35
    've
    1.02
     wrote
    1.00
    're
    0.90
    zbollah
    0.89
     undertook
    0.87
     oversaw
    0.87
     became
    0.86
     boarded
    0.86
    Act Density 0.241%

    No Known Activations