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

    Neuronpedia

    INDEX
    Explanations

    website subscription-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to subscribing, signing up, or joining something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagen
    -0.83
     fortun
    -0.73
     fung
    -0.72
     unaccount
    -0.71
    wagon
    -0.71
     Klu
    -0.70
     attm
    -0.69
     unconscious
    -0.69
    Ĥª
    -0.69
     horizont
    -0.68
    POSITIVE LOGITS
     receive
    0.75
    orate
    0.72
     improve
    0.72
     subscribe
    0.70
     customize
    0.66
     refresh
    0.65
     update
    0.64
     regain
    0.64
     Ø
    0.64
     get
    0.64
    Act Density 0.047%

    No Known Activations