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

    Neuronpedia

    INDEX
    Explanations

    detailed observations and measurements captured in images

    oai_token-act-pair · gpt-3.5-turbo

    references to visual data and measurements in scientific observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     boycot
    -0.73
     Rebell
    -0.73
     disliked
    -0.69
     pacif
    -0.65
    iquette
    -0.65
    advertising
    -0.64
    oiler
    -0.64
     Quit
    -0.63
     Masquerade
    -0.63
     circumstance
    -0.62
    POSITIVE LOGITS
    atellite
    0.92
     datasets
    0.90
     satellites
    0.89
     microsc
    0.86
     infrared
    0.86
     electron
    0.84
    metry
    0.82
    rared
    0.82
     wavelengths
    0.81
    atell
    0.81
    Act Density 0.204%

    No Known Activations