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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence of the word "we" and its variations, suggesting a focus on collective action or group perspective

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     now
    -0.31
     recently
    -0.30
     soon
    -0.26
     lately
    -0.25
     recent
    -0.24
    now
    -0.23
     ahora
    -0.23
    recent
    -0.23
     currently
    -0.22
     nynÃŃ
    -0.21
    POSITIVE LOGITS
     again
    0.20
     will
    0.17
     Again
    0.17
    ake
    0.16
    Again
    0.16
    again
    0.15
     instead
    0.15
     Instead
    0.15
     weer
    0.15
    illion
    0.14
    Act Density 0.023%

    No Known Activations