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

    Neuronpedia

    INDEX
    Explanations

    phrases related to setting goals or being on a certain path

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating positive progress or growth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amiya
    -0.74
    mr
    -0.66
    essee
    -0.63
     embodiment
    -0.62
     contexts
    -0.61
    iae
    -0.60
    iverpool
    -0.60
     @@
    -0.58
     Chattanooga
    -0.57
     Mous
    -0.57
    POSITIVE LOGITS
     pedest
    1.19
     bandwagon
    1.11
     footing
    1.01
     treadmill
    1.00
     trajectory
    0.99
     leash
    0.99
     wavelength
    0.93
     rampage
    0.91
     continuum
    0.90
     radar
    0.90
    Act Density 0.106%

    No Known Activations