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

    Neuronpedia

    INDEX
    Explanations

    elements related to textual references or academic jargon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .lu
    -0.16
     triang
    -0.16
    족
    -0.15
    umont
    -0.14
    oval
    -0.14
    cke
    -0.14
    uml
    -0.14
    agua
    -0.14
    ylon
    -0.14
    gnore
    -0.13
    POSITIVE LOGITS
    aze
    0.16
     Kho
    0.16
    ngo
    0.15
    CHASE
    0.14
    ted
    0.14
    AZE
    0.14
    REAK
    0.14
    çĪ·
    0.14
     inter
    0.13
    undle
    0.13
    Act Density 0.004%

    No Known Activations