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

    Neuronpedia

    INDEX
    Explanations

    nuances of existence and conditionality in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bebasan
    -0.60
     termica
    -0.55
     particulière
    -0.53
     telles
    -0.53
    sibilità
    -0.51
     výbě
    -0.50
     väx
    -0.50
     rosse
    -0.50
     gué
    -0.50
     antichi
    -0.49
    POSITIVE LOGITS
    "])
    0.87
    PreferredItem
    0.84
     very
    0.81
    "):
    0.81
    )");
    0.81
     """
    0.78
     highly
    0.76
     quite
    0.74
    extAlignment
    0.74
    "],
    0.74
    Act Density 0.549%

    No Known Activations