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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating fundamental implications or explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     col
    -0.69
     en
    -0.68
     po
    -0.63
     in
    -0.62
     che
    -0.59
     a
    -0.59
     y
    -0.59
     (
    -0.59
     Col
    -0.58
     de
    -0.58
    POSITIVE LOGITS
     Efq
    1.56
     Monfieur
    1.56
     Reſ
    1.40
     myſelf
    1.38
     purpoſe
    1.38
     itſelf
    1.35
    ſelf
    1.35
     Houſe
    1.34
     ―――――
    1.34
     ſtate
    1.30
    Act Density 0.223%

    No Known Activations