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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by an action or description

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating limitations or lack of significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dane
    -0.71
    cember
    -0.69
     hires
    -0.67
     jan
    -0.65
    士
    -0.64
     pregnancies
    -0.64
     layoffs
    -0.63
     salaries
    -0.62
     motions
    -0.60
     visc
    -0.60
    POSITIVE LOGITS
     satisfy
    1.02
    asted
    0.94
     celebrate
    0.89
    adies
    0.88
    ggles
    0.87
     relieve
    0.86
    pload
    0.85
     appease
    0.85
     justify
    0.84
     reinforce
    0.83
    Act Density 0.111%

    No Known Activations