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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific authors and their contributions in academic references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    verts
    -0.15
     gore
    -0.15
    егоÑĢ
    -0.14
    erts
    -0.14
    reib
    -0.14
    elsen
    -0.14
     Newman
    -0.14
     Dag
    -0.13
    lastic
    -0.13
    rel
    -0.13
    POSITIVE LOGITS
    jer
    0.16
     chai
    0.16
    cles
    0.14
     Cah
    0.14
    lernen
    0.14
     serializers
    0.14
    ÙĦع
    0.14
    ë¶
    0.13
    WO
    0.13
     calcul
    0.13
    Act Density 0.004%

    No Known Activations