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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating returning or coming back from a location or situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edl
    -0.18
    _regularizer
    -0.16
    \Blueprint
    -0.14
    apan
    -0.14
    eru
    -0.14
    taire
    -0.14
    .digest
    -0.14
    .tk
    -0.14
    edir
    -0.14
    ceph
    -0.13
    POSITIVE LOGITS
     <!--[
    0.15
     Ricky
    0.14
    ward
    0.14
    ien
    0.14
    Toolkit
    0.14
    Toe
    0.14
     Tear
    0.13
    нÑİ
    0.13
    hou
    0.13
     Sick
    0.13
    Act Density 0.024%

    No Known Activations