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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "In."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "In" followed by a numerical value or significant label

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lett
    -0.71
     spoil
    -0.68
    ¶æ
    -0.68
     lodged
    -0.67
     litter
    -0.64
    llan
    -0.62
     bye
    -0.60
     heights
    -0.60
     chall
    -0.60
     flagged
    -0.60
    POSITIVE LOGITS
    jection
    1.44
    jured
    1.39
    jected
    1.36
    clusion
    1.34
    herent
    1.29
    clusive
    1.28
    flation
    1.25
    strument
    1.25
    ject
    1.25
    clus
    1.23
    Act Density 0.135%

    No Known Activations