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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical actions involving specific body parts

    oai_token-act-pair · gpt-3.5-turbo

    situations involving physical interactions or significant actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essor
    -0.61
    Reviewer
    -0.54
     abound
    -0.51
    omorph
    -0.51
    -)
    -0.50
    ptions
    -0.50
     prod
    -0.49
     exceptions
    -0.48
     perceive
    -0.48
    ggles
    -0.48
    POSITIVE LOGITS
     yesterday
    0.84
     shortly
    0.81
     Thursday
    0.75
     Wednesday
    0.75
     today
    0.72
     Tuesday
    0.71
     tonight
    0.71
    terday
    0.70
     Monday
    0.65
     intending
    0.64
    Act Density 1.158%

    No Known Activations