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

    Neuronpedia

    INDEX
    Explanations

    variations of the verb "to be" in different contexts

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

    Contractions with "it is"

    np_acts-logits-general · gemini-2.0-flash

    It's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SBATCH
    -0.63
    queryInterface
    -0.62
     autorytatywna
    -0.60
    RenderAtEndOf
    -0.60
    rzej
    -0.58
    aarrggbb
    -0.58
    wegg
    -0.56
    ListItemIcon
    -0.55
    Rohy
    -0.54
     useContext
    -0.54
    POSITIVE LOGITS
     simple
    0.73
     always
    0.71
     certainly
    0.64
     unfortunate
    0.63
     never
    0.62
    之所以
    0.60
     sad
    0.60
     not
    0.59
     true
    0.57
     funny
    0.56
    Act Density 0.144%

    No Known Activations