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

    Neuronpedia

    INDEX
    Explanations

    references to cards or card-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ously
    -0.18
    ırak
    -0.16
    erties
    -0.16
    -cn
    -0.16
    olu
    -0.16
    icz
    -0.16
    rok
    -0.15
    OUS
    -0.15
    usement
    -0.15
    estone
    -0.15
    POSITIVE LOGITS
    .Card
    0.25
    inality
    0.25
    igan
    0.24
    iology
    0.24
    inals
    0.24
    /Card
    0.24
    INAL
    0.23
     card
    0.23
    inal
    0.23
    .card
    0.22
    Act Density 0.010%

    No Known Activations