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

    Neuronpedia

    INDEX
    Explanations

    phrases related to financial transactions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     makro
    -1.47
     antik
    -1.44
     alkoh
    -1.43
     marte
    -1.34
     umo
    -1.34
     tuta
    -1.31
     Kategor
    -1.31
     maroc
    -1.30
     elek
    -1.29
     ananas
    -1.29
    POSITIVE LOGITS
     but
    0.91
     they
    0.69
     yes
    0.67
     we
    0.66
     however
    0.66
     nhưng
    0.64
    but
    0.64
     pero
    0.63
     and
    0.63
     he
    0.62
    Act Density 0.410%

    No Known Activations