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

    Neuronpedia

    INDEX
    Explanations

    references to inclusion or the presence of items in a set

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĬãĤĬ
    -0.25
    REATED
    -0.15
    iggers
    -0.15
    .uk
    -0.15
    ë§Īëĭ¤
    -0.15
    ickle
    -0.14
    pered
    -0.14
    uel
    -0.14
    kup
    -0.14
    chedulers
    -0.14
    POSITIVE LOGITS
    /ex
    0.34
     cả
    0.18
    ognito
    0.18
    graphics
    0.17
    /un
    0.16
     everything
    0.15
    /embed
    0.15
     provisions
    0.15
    سÙĩ
    0.15
    ARY
    0.15
    Act Density 0.106%

    No Known Activations