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

    Neuronpedia

    INDEX
    Explanations

    subscription-related instructions or calls to action with an emphasis on email sign-ups

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to signing up for newsletters or subscriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynt
    -0.65
    tten
    -0.64
     Haas
    -0.64
    pure
    -0.63
    abal
    -0.62
     hurd
    -0.61
    kell
    -0.59
    gran
    -0.59
     Palmer
    -0.58
    hend
    -0.58
    POSITIVE LOGITS
     guiActive
    0.74
     Password
    0.74
     unlocks
    0.72
     Username
    0.67
    ãģı
    0.67
    irmation
    0.66
    again
    0.66
    Sorry
    0.66
    Streamer
    0.66
     Sign
    0.65
    Act Density 0.036%

    No Known Activations