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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating collective effort or the involvement of multiple entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aktu
    -0.16
    IBLE
    -0.16
     sometimes
    -0.15
    UGHT
    -0.15
    yu
    -0.15
    åĨĴ
    -0.15
     as
    -0.14
     dam
    -0.14
    OFFSET
    -0.14
     often
    -0.14
    POSITIVE LOGITS
    loquent
    0.17
    unge
    0.17
    ायà¤ķ
    0.15
    ìķł
    0.15
    egral
    0.15
    ackers
    0.15
     gezocht
    0.15
     Äijá»ģu
    0.15
    à¹Ĥà¸ķ
    0.14
     éĥ½
    0.14
    Act Density 0.122%

    No Known Activations