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

    Neuronpedia

    INDEX
    Explanations

    words that indicate circumstances or qualifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     informée
    -0.61
     चीज़ों
    -0.60
    Попис
    -0.60
    彡
    -0.60
    ToDelete
    -0.60
    ();)
    -0.59
    AnchorStyles
    -0.56
    UserScript
    -0.55
    giveness
    -0.55
     تانيه
    -0.54
    POSITIVE LOGITS
    Perhaps
    0.92
    While
    0.91
    Although
    0.90
    Because
    0.89
    Moreover
    0.88
    Recently
    0.87
     Likewise
    0.87
    Likewise
    0.86
    Additionally
    0.86
    Generally
    0.86
    Act Density 0.634%

    No Known Activations