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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     A
    -0.65
     The
    -0.64
    TRES
    -0.64
    GLOBALS
    -0.63
     a
    -0.62
     MacGregor
    -0.61
     McGregor
    -0.60
    Pp
    -0.60
     Mar
    -0.59
     Menon
    -0.58
    POSITIVE LOGITS
     dieß
    1.03
     ―――――
    1.02
     ſche
    1.00
    Personensuche
    1.00
     Dage
    0.98
     myſelf
    0.96
     Diretto
    0.94
    ."));
    0.94
    ……"
    0.92
    Datuak
    0.92
    Act Density 1.005%

    No Known Activations