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

    Neuronpedia

    INDEX
    Explanations

    phrases related to finality or ultimatums

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "last" alongside references to events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    baum
    -0.71
    Gameplay
    -0.70
    detail
    -0.70
    orf
    -0.69
    ustomed
    -0.68
    urat
    -0.68
    iets
    -0.66
    tiny
    -0.65
    gravity
    -0.64
    olor
    -0.64
    POSITIVE LOGITS
     goodbye
    0.90
     Alive
    0.83
     farewell
    0.79
     alive
    0.77
     gasp
    0.70
    quit
    0.69
     salute
    0.69
     Aval
    0.69
     checked
    0.68
     extinguished
    0.67
    Act Density 0.123%

    No Known Activations