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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments or expressions of dissatisfaction

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

    Token before a number

    np_acts-logits-general · gemini-2.0-flash

    bibliographic references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    both
    -0.56
     both
    -0.54
    ...
    -0.49
    !
    -0.49
    Literatura
    -0.47
     ...
    -0.47
    *
    -0.46
     the
    -0.45
    Примітки
    -0.45
     *
    -0.45
    POSITIVE LOGITS
     raiſ
    0.85
     ſever
    0.81
     poffe
    0.78
     fevere
    0.78
     faſt
    0.77
     ſta
    0.77
     Monfieur
    0.73
     ſche
    0.73
     Charlemagne
    0.73
     greateſt
    0.72
    Act Density 0.313%

    No Known Activations