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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and significant names associated with individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ullet
    -0.17
    arro
    -0.17
    mmo
    -0.16
    бÑĥ
    -0.15
    772
    -0.15
    398
    -0.15
    288
    -0.15
    ipple
    -0.15
    ková
    -0.15
    rape
    -0.14
    POSITIVE LOGITS
    Americ
    0.16
    ery
    0.15
    umer
    0.15
    erif
    0.14
    antz
    0.14
    ama
    0.14
     Feld
    0.14
    æ°Ĺ
    0.14
    pd
    0.14
    ůž
    0.14
    Act Density 0.030%

    No Known Activations