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

    Neuronpedia

    INDEX
    Explanations

    phrases that suggest a sense of time or continuity since a past event

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    extAlignment
    -0.91
     CRS
    -0.88
     nahilalakip
    -0.82
     SLS
    -0.82
     SANS
    -0.80
     Vichy
    -0.80
     sni
    -0.79
     Cham
    -0.79
    Schneider
    -0.79
    SourceChecksum
    -0.79
    POSITIVE LOGITS
     mawar
    0.69
     passés
    0.65
    or
    0.62
    iver
    0.62
     over
    0.61
     décédé
    0.61
    TimeUnit
    0.60
     even
    0.59
    Oster
    0.59
     Bab
    0.58
    Act Density 0.010%

    No Known Activations