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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "go" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unto
    -0.17
    ÙĨدÙĩ
    -0.14
    umin
    -0.14
    piler
    -0.14
    pool
    -0.14
     Lust
    -0.14
    quis
    -0.14
     Ders
    -0.14
    uously
    -0.14
    logen
    -0.14
    POSITIVE LOGITS
    Go
    0.29
     Go
    0.28
    -go
    0.25
    thic
    0.23
    ût
    0.22
     go
    0.22
    ody
    0.21
    (go
    0.20
     figure
    0.20
    tha
    0.19
    Act Density 0.024%

    No Known Activations