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

    Neuronpedia

    INDEX
    Explanations

    instances of reported speech and formal communication

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

    reporting speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.60
    jména
    -0.43
     prohibido
    -0.42
     normalidad
    -0.42
     ningún
    -0.42
     pájaro
    -0.42
     pauvres
    -0.40
     gustar
    -0.39
     colchón
    -0.38
     mitään
    -0.38
    POSITIVE LOGITS
     quoted
    0.53
    MessageOf
    0.51
     echoed
    0.48
     quotes
    0.47
    AccessorTable
    0.46
     interviews
    0.46
    quoted
    0.45
     asser
    0.45
    发表于
    0.43
     POW
    0.43
    Act Density 0.022%

    No Known Activations