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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "abide" and its forms

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

    abide by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nonUne
    -0.70
    NewUrl
    -0.54
    Guns
    -0.54
     DataLoader
    -0.53
    IBOutlet
    -0.53
    estacks
    -0.52
     CTV
    -0.52
    üyada
    -0.52
    qiu
    -0.50
    ectady
    -0.50
    POSITIVE LOGITS
     abide
    1.64
     abiding
    1.31
     adhere
    0.55
     adheres
    0.55
     abode
    0.55
     adhering
    0.55
    遵守
    0.53
     stay
    0.53
     Stay
    0.52
    Stayed
    0.52
    Act Density 0.004%

    No Known Activations