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

    Neuronpedia

    INDEX
    Explanations

    instances of temporal phrases indicating sequences of events

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

    "before" indicating a sequence

    np_acts-logits-general · gemini-2.0-flash

    before eventual state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     становника
    -0.48
    expandindo
    -0.47
     utafitiHapana
    -0.45
     ſche
    -0.44
     Inſ
    -0.41
    cmake
    -0.40
     tranſ
    -0.40
    Manufacturers
    -0.39
    MFG
    -0.38
    Välislingid
    -0.38
    POSITIVE LOGITS
     eventually
    0.78
    Eventually
    0.76
     Eventually
    0.75
    eventually
    0.74
     finally
    0.74
    finally
    0.63
     eventual
    0.63
     Finally
    0.63
    最终
    0.63
    Finally
    0.62
    Act Density 0.499%

    No Known Activations