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

    Neuronpedia

    INDEX
    Explanations

    questions that introduce a subject for discussion or inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unday
    -0.18
    opus
    -0.18
     ÑĥÑģÑĤ
    -0.15
    estroy
    -0.14
    bih
    -0.14
    aced
    -0.14
    aces
    -0.14
    не
    -0.14
    unden
    -0.14
    criptor
    -0.14
    POSITIVE LOGITS
    oS
    0.19
    naires
    0.19
    ubit
    0.18
    estion
    0.18
    wick
    0.18
    rcode
    0.18
    &A
    0.18
    ues
    0.17
    wert
    0.17
    o
    0.17
    Act Density 0.033%

    No Known Activations