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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technological processes and programming references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.08
     myſelf
    -1.06
     doubtnut
    -1.05
     themſelves
    -1.03
     ་་
    -1.02
    ſelves
    -1.02
     greateſt
    -1.01
     ―――――
    -1.00
    Билгалдахарш
    -0.98
     Houſe
    -0.98
    POSITIVE LOGITS
     i
    0.64
     K
    0.62
     E
    0.61
     N
    0.56
     I
    0.55
     (
    0.54
     V
    0.53
     et
    0.53
    ^
    0.52
     S
    0.52
    Act Density 1.343%

    No Known Activations