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

    Neuronpedia

    INDEX
    Explanations

    phrases related to subscriptions and notifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onso
    -0.15
    loss
    -0.15
    ëĨį
    -0.14
    936
    -0.14
    ard
    -0.14
    ive
    -0.14
    edback
    -0.14
    MouseButton
    -0.14
    436
    -0.14
    stab
    -0.14
    POSITIVE LOGITS
    unsubscribe
    0.19
     unsub
    0.18
     unsubscribe
    0.17
    IKE
    0.16
    yg
    0.16
     kê
    0.15
     relent
    0.14
     Privacy
    0.14
    ãĥ³ãĥĸ
    0.14
     privacy
    0.14
    Act Density 0.032%

    No Known Activations