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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -2.09
     Monfieur
    -2.05
     myſelf
    -2.03
    ^(@)
    -1.95
     Theſe
    -1.93
     Jefus
    -1.92
     Majefty
    -1.91
     Houſe
    -1.86
     itſelf
    -1.83
     Reſ
    -1.77
    POSITIVE LOGITS
     that
    1.55
     That
    1.28
    <eos>
    1.22
    that
    1.20
    That
    1.20
     
    1.11
     (
    1.09
    ,
    1.02
    -
    1.02
    .
    1.00
    Act Density 0.182%

    No Known Activations