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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating an action or purpose

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating purpose or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Typ
    -0.75
    wrote
    -0.70
    writ
    -0.69
     Printed
    -0.66
     snipp
    -0.66
     Steps
    -0.66
    loads
    -0.64
    said
    -0.62
     Orange
    -0.61
    prints
    -0.61
    POSITIVE LOGITS
     maximize
    1.51
     minimize
    1.50
     avoid
    1.42
     preserve
    1.41
     conserve
    1.40
     lessen
    1.37
     appease
    1.31
     facilitate
    1.31
     prevent
    1.26
     regain
    1.24
    Act Density 0.155%

    No Known Activations