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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "cop" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Leod
    -0.14
    ctica
    -0.14
    quam
    -0.14
    voke
    -0.14
    /vector
    -0.14
    hoo
    -0.14
    еÑĢÑĪ
    -0.14
    ãĤĵ
    -0.14
     Trident
    -0.14
    lej
    -0.14
    POSITIVE LOGITS
    eland
    0.16
    .deepcopy
    0.15
     Cop
    0.15
    lush
    0.15
    /cop
    0.14
    cha
    0.14
    ilot
    0.14
    SWEP
    0.14
    escal
    0.14
    emann
    0.14
    Act Density 0.029%

    No Known Activations