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

    Neuronpedia

    INDEX
    Explanations

    phrases related to application processes and restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fair
    -0.18
    ehr
    -0.15
    eut
    -0.15
    alo
    -0.15
     Stam
    -0.14
    ẩy
    -0.14
    ucci
    -0.14
    leur
    -0.14
    vr
    -0.14
    agem
    -0.14
    POSITIVE LOGITS
     nor
    0.18
     cannot
    0.16
    _sdk
    0.15
     please
    0.15
    QS
    0.15
    CAA
    0.15
    chg
    0.14
    hangi
    0.14
    iker
    0.14
    warf
    0.14
    Act Density 0.066%

    No Known Activations