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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ongoing patterns or historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inesperado
    -0.59
     تازه
    -0.57
     GenerationType
    -0.56
    prnewswire
    -0.55
     Lordships
    -0.55
     esterni
    -0.54
    ifrance
    -0.51
    cosis
    -0.51
    creativecommons
    -0.51
     fresh
    -0.50
    POSITIVE LOGITS
    一直
    0.73
    以來
    0.73
    ずっと
    0.71
    Siempre
    0.70
     Always
    0.67
     depuis
    0.66
     Siempre
    0.66
    我一直
    0.66
    deauna
    0.65
     since
    0.65
    Act Density 0.224%

    No Known Activations