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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "subscribe" appears

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to subscriptions and newsletters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynchronous
    -0.76
    cffffcc
    -0.72
    imposed
    -0.68
    hooting
    -0.67
    igil
    -0.67
    inois
    -0.67
    olesc
    -0.65
    ync
    -0.63
    eneg
    -0.63
    framework
    -0.63
    POSITIVE LOGITS
     receive
    0.92
     our
    0.82
     Metal
    0.74
     Charisma
    0.68
     Discover
    0.64
     Feed
    0.64
     Rate
    0.63
     Raw
    0.63
     Decay
    0.63
     Our
    0.62
    Act Density 0.046%

    No Known Activations