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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the start of a discussion or argument, often emphasizing initial points or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Geplaatst
    -0.91
     Houſe
    -0.89
     houſe
    -0.88
     ſeveral
    -0.85
     purpoſe
    -0.83
     Majefty
    -0.82
     ſtate
    -0.81
    XmlAccessorType
    -0.81
     Efq
    -0.79
     fevere
    -0.78
    POSITIVE LOGITS
    Firstly
    1.01
     Firstly
    0.98
     firstly
    0.84
    首先
    0.78
    первых
    0.76
    まず
    0.75
    First
    0.71
     First
    0.70
    Primero
    0.70
     primero
    0.62
    Act Density 0.220%

    No Known Activations