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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases in formal agreements or contracts

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

    appearing before nouns

    np_acts-logits-general · gemini-2.0-flash

    listing conjunctions with terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     juntamente
    -0.33
     además
    -0.32
     either
    -0.30
    Inclu
    -0.28
     terutama
    -0.28
     ninguno
    -0.28
    Hlav
    -0.28
    either
    -0.28
     you
    -0.27
    ColumnName
    -0.27
    POSITIVE LOGITS
     Infórmanos
    0.81
     zwiſchen
    0.80
     kasarigan
    0.79
    <unused52>
    0.78
    <unused23>
    0.77
    <unused14>
    0.77
    <unused41>
    0.77
    <unused68>
    0.77
    <unused47>
    0.77
    <pad>
    0.77
    Act Density 0.357%

    No Known Activations