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

    Neuronpedia

    INDEX
    Explanations

    references to research institutions, universities, and their locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.62
     ſta
    -0.42
    badlogic
    -0.41
    ุทธ
    -0.41
     Reſ
    -0.40
    cension
    -0.40
     rall
    -0.40
    Philly
    -0.40
    Hochspringen
    -0.40
    verwijspagina
    -0.40
    POSITIVE LOGITS
    ьаж
    0.54
    PO
    0.49
     PO
    0.47
    0.46
    ONSORED
    0.44
     Partner
    0.42
    Décès
    0.41
    Varint
    0.41
    CHAFT
    0.40
     Box
    0.40
    Act Density 0.373%

    No Known Activations