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

    Neuronpedia

    INDEX
    Explanations

    actions related to work or effort

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating efforts or actions taken towards a goal or outcome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     glances
    -0.70
     Used
    -0.70
    quartered
    -0.69
     Cust
    -0.68
    faces
    -0.67
     Malf
    -0.66
     curs
    -0.65
     Spaces
    -0.65
     Moments
    -0.64
    Lot
    -0.62
    POSITIVE LOGITS
     promote
    1.28
    ggles
    1.20
     improve
    1.19
     minimize
    1.15
     emulate
    1.15
     conserve
    1.14
     achieve
    1.12
     accommodate
    1.12
     preserve
    1.11
     ensure
    1.11
    Act Density 0.203%

    No Known Activations