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

    Neuronpedia

    INDEX
    Explanations

    numerical values, particularly those represented as fractions or decimals, often in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     A
    -0.70
     The
    -0.68
    maco
    -0.64
     C
    -0.64
      
    -0.64
     qu
    -0.62
    tC
    -0.62
     Two
    -0.61
     F
    -0.61
     a
    -0.60
    POSITIVE LOGITS
    Datuak
    1.31
     ―――――
    1.24
     dieß
    1.23
     Majefty
    1.19
     ſche
    1.11
     myſelf
    1.11
     ISNI
    1.11
     Diretto
    1.10
     itſelf
    1.08
     Diſ
    1.04
    Act Density 0.488%

    No Known Activations