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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of the verb "to be" in various languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     DefaultValue
    -0.15
    itters
    -0.15
    tility
    -0.15
    .localized
    -0.14
    еÑĢÑĪ
    -0.14
    emachine
    -0.14
     меÑħ
    -0.14
    ãĥĭãĥ¼
    -0.14
    æĤ
    -0.14
    ìļķ
    -0.14
    POSITIVE LOGITS
    ocrates
    0.15
     Cabinet
    0.15
    angered
    0.15
    udas
    0.15
    æĽ²
    0.14
    ander
    0.14
    ucci
    0.14
     Apprent
    0.14
    abelle
    0.14
    zan
    0.14
    Act Density 0.010%

    No Known Activations