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

    Neuronpedia

    INDEX
    Explanations

    words and phrases associated with subscription actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    subscribe to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ことができ
    -0.50
    ことができる
    -0.46
    WV
    -0.45
     inca
    -0.42
    ことができます
    -0.41
    new
    -0.41
     imperfections
    -0.39
    ton
    -0.39
     Ivar
    -0.39
     Malden
    -0.38
    POSITIVE LOGITS
    Subscribe
    1.85
     subscribe
    1.84
     Subscribe
    1.74
    subscribe
    1.65
     subscribing
    1.49
     subscribed
    1.45
     SUBSCRIBE
    1.38
    ubscribe
    1.36
    SUBSCRIBE
    1.27
     subscri
    1.24
    Act Density 0.006%

    No Known Activations