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

    Neuronpedia

    INDEX
    Explanations

    instances of uncertainty or indecision

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .ua
    -0.21
    allon
    -0.20
    udas
    -0.17
    -cn
    -0.16
    è¾°
    -0.16
    /Dk
    -0.16
    RAY
    -0.16
    orns
    -0.16
    anyl
    -0.15
    ourd
    -0.15
    POSITIVE LOGITS
    er
    0.15
    iselect
    0.15
    extern
    0.15
    prite
    0.14
    ãĤĵãģ§ãģĦãĤĭ
    0.14
     Tor
    0.14
     QVariant
    0.14
    HCI
    0.14
     fre
    0.14
    InstanceOf
    0.14
    Act Density 0.004%

    No Known Activations