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

    Neuronpedia

    INDEX
    Explanations

    the word "apparently" as a marker of assumptions or statements about the perceived state of affairs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UVWXYZ
    -0.64
     crescita
    -0.59
     ATC
    -0.58
     inovasi
    -0.56
     acceso
    -0.56
    lück
    -0.55
     attiv
    -0.53
     δυνα
    -0.52
     Rox
    -0.52
     spørsmål
    -0.51
    POSITIVE LOGITS
     apparently
    3.00
    apparently
    2.92
     Apparently
    2.79
    Apparently
    2.76
     supposedly
    2.42
     allegedly
    2.34
     reportedly
    2.25
     evidently
    2.15
     aparentemente
    2.14
     presumably
    2.05
    Act Density 0.054%

    No Known Activations