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

    Neuronpedia

    INDEX
    Explanations

    phrases that signify causation or relationships between events

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

    turn leading to consequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    chieht
    -0.56
     صوتيه
    -0.55
     propOrder
    -0.53
     feroit
    -0.50
     않았
    -0.49
     sò
    -0.48
    agisse
    -0.48
     sibi
    -0.47
     noires
    -0.47
     auroit
    -0.46
    POSITIVE LOGITS
     wiederum
    0.65
     Затем
    0.43
    RepeatedField
    0.42
    Gambas
    0.42
    又要
    0.41
     turn
    0.38
     conseguenza
    0.38
     ensuing
    0.38
    Затем
    0.37
    ṃ
    0.37
    Act Density 0.010%

    No Known Activations