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

    Neuronpedia

    INDEX
    Explanations

    references to time, stages, or processes related to transitions and changes

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

    Comes after words indicating sequence or time

    np_acts-logits-general · gemini-2.0-flash

    sequence and timing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.42
    tall
    -0.35
    pad
    -0.32
     miglia
    -0.31
     fundas
    -0.30
     Einf
    -0.30
    achat
    -0.30
     tall
    -0.30
    olo
    -0.29
    offrir
    -0.29
    POSITIVE LOGITS
     चीज़ों
    0.65
    parsedMessage
    0.63
    Após
    0.56
    Setelah
    0.54
     setelah
    0.54
    After
    0.53
    Nachdem
    0.53
    После
    0.52
    Depois
    0.52
    UnknownFieldSet
    0.52
    Act Density 1.174%

    No Known Activations