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

    Neuronpedia

    INDEX
    Explanations

    symbols or characters that indicate links or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tind
    -0.71
     
    -0.69
     cut
    -0.65
    -
    -0.65
     (
    -0.64
     daw
    -0.62
    /
    -0.62
    奴
    -0.61
    ̯
    -0.60
    (
    -0.60
    POSITIVE LOGITS
     avoient
    1.22
     étoit
    1.20
     Monfieur
    1.19
     Jefus
    1.16
     uſed
    1.15
     feroit
    1.14
     poffible
    1.13
     étoient
    1.13
     myſelf
    1.12
     ainfi
    1.12
    Act Density 0.348%

    No Known Activations