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

    Neuronpedia

    INDEX
    Explanations

    phrases related to email subscription and receiving information

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Shay
    -0.58
     Barnett
    -0.56
    olkien
    -0.56
    livious
    -0.55
    bush
    -0.54
     moot
    -0.54
    ijing
    -0.54
     Mankind
    -0.54
     Eliot
    -0.53
    asers
    -0.53
    POSITIVE LOGITS
    interstitial
    0.80
    $$$$
    0.70
     unlocks
    0.68
    select
    0.66
    icka
    0.65
    aunder
    0.64
    "]=>
    0.63
    login
    0.61
     Login
    0.61
    cgi
    0.61
    Act Density 0.033%

    No Known Activations