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

    Neuronpedia

    INDEX
    Explanations

    words signaling contrast or contradiction

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

    introducing a contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Дереккөздер
    -0.60
     springfox
    -0.56
    TagMode
    -0.54
    Personendaten
    -0.52
     useAppContext
    -0.52
     uLocal
    -0.52
    SourceChecksum
    -0.52
    ChildScrollView
    -0.52
    ⤹
    -0.51
     invokingState
    -0.50
    POSITIVE LOGITS
    fork
    0.41
     voisins
    0.38
    nullptr
    0.37
    suggested
    0.36
    Cant
    0.36
     Daher
    0.36
    neighbour
    0.36
    recommended
    0.35
     sottile
    0.35
    advised
    0.35
    Act Density 0.056%

    No Known Activations