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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time, events, descriptions, and actions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific events, conditions, or measurements relating to time and place

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ritis
    -0.80
    encers
    -0.79
    auts
    -0.78
    ocate
    -0.75
    haar
    -0.73
    ¶ħ
    -0.73
    atron
    -0.71
    ngth
    -0.71
    =-=-=-=-
    -0.71
    raint
    -0.68
    POSITIVE LOGITS
     occasions
    1.16
     basis
    1.16
     behalf
    1.05
     footing
    0.92
     occasion
    0.92
     grounds
    0.88
     pretext
    0.87
     fronts
    0.83
     eve
    0.81
     bandwagon
    0.80
    Act Density 1.054%

    No Known Activations