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

    Neuronpedia

    INDEX
    Explanations

    instances of personal history and biographical details

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

    After an initial activity or event

    np_acts-logits-general · gemini-2.0-flash

    became, started, returned, joined

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    [@BOS@]
    -0.79
    <unused42>
    -0.79
    <unused8>
    -0.79
    <unused16>
    -0.78
    -0.78
    <unused28>
    -0.78
    <unused41>
    -0.78
    <unused79>
    -0.78
    <unused74>
    -0.78
    <pad>
    -0.78
    POSITIVE LOGITS
     başlad
    0.30
     ardından
    0.28
     juventud
    0.28
     inicialmente
    0.27
     begann
    0.26
     career
    0.25
     пришла
    0.25
     eventually
    0.25
    invokeLater
    0.24
     carteira
    0.24
    Act Density 0.222%

    No Known Activations